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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14279
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms related to statistics and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     تضيفلها
    -0.63
    tagHelperRunner
    -0.57
     Italij
    -0.55
    Spolja
    -0.55
    httphttps
    -0.55
    niſſe
    -0.55
    RTCK
    -0.54
    Życiorys
    -0.54
     Anreg
    -0.54
    jenigen
    -0.52
    POSITIVE LOGITS
    </b>
    0.81
    </h2>
    0.76
    </h3>
    0.75
    </strong>
    0.71
    </u>
    0.63
    </h4>
    0.62
    </h1>
    0.53
    </i>
    0.50
    0.43
    </h5>
    0.42
    Activations Density 0.500%

    No Known Activations