© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11971
    Prev
    Next
    INDEX
    Explanations

    key performance indicators and metrics related to advertising and audience engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    patterns and technical termsThis is a 4-word explanation derived from "patterns", "signaling", "Cells", "makers" and considering the technical nature suggested by "transfection", "transfectants", "IUrlHelper", "Demografie", and the structure often found in scientific/technical documents (headings from TOP_POSITIVE_LOGITS). The "and" from MAX_ACTIVATING_TOKENS is also key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.58
    Manbalar
    -0.57
     Geſch
    -0.56
     تضيفلها
    -0.56
    niſſe
    -0.56
    jenigen
    -0.55
     Italij
    -0.55
    Spolja
    -0.54
    İstinadlar
    -0.53
    enumi
    -0.52
    POSITIVE LOGITS
    </h2>
    0.68
    </b>
    0.67
    </h3>
    0.64
    </strong>
    0.58
    </u>
    0.53
    </h4>
    0.48
    </h1>
    0.47
    Demografie
    0.41
    </i>
    0.39
    IUrlHelper
    0.38
    Activations Density 0.440%

    No Known Activations