© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11187
    Prev
    Next
    INDEX
    Explanations

    specific criteria and procedural details in technical or legal documents

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

    preceding a period, comma, or "that"

    np_acts-logits-general · gemini-2.0-flash

    specifications and details

    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
     Numerade
    -0.67
    Personensuche
    -0.65
    windowFixed
    -0.63
    SequentialGroup
    -0.60
    tagext
    -0.59
    SharedCtor
    -0.57
    tagHelperRunner
    -0.56
    Personendaten
    -0.56
     becauſe
    -0.55
    ✨:
    -0.53
    POSITIVE LOGITS
     manipulations
    0.38
     manipulation
    0.38
     manipulated
    0.37
    manip
    0.36
     nuances
    0.36
     involving
    0.36
    ilerini
    0.34
    reiben
    0.34
    inaison
    0.33
     projections
    0.33
    Activations Density 1.038%

    No Known Activations