© 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. 1419
    Prev
    Next
    INDEX
    Explanations

    elements related to web development and resource integrity checks

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

    Article or website URLs and identifiers

    np_acts-logits-general · gemini-2.0-flash

    URLs and identifiers

    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
     simplifié
    -0.44
     Municipalidad
    -0.44
    ########.
    -0.44
     RouterModule
    -0.42
    TintMode
    -0.41
    yntaxException
    -0.40
    membership
    -0.40
     useAuth
    -0.40
     considérons
    -0.39
    btnClose
    -0.39
    POSITIVE LOGITS
    TagMode
    0.96
    eqn
    0.95
    AndEndTag
    0.91
    bootstrapcdn
    0.83
    VIAF
    0.77
    findpost
    0.68
    SequentialGroup
    0.67
    MessageOf
    0.63
    ftagPool
    0.59
    GraphicsUnit
    0.58
    Activations Density 0.174%

    No Known Activations