© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 3424
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly colons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.91
    CloseOperation
    -0.74
    InputBorder
    -0.70
    DockStyle
    -0.68
    ContentAsync
    -0.67
    ArgsConstructor
    -0.66
    featureID
    -0.66
    رشف
    -0.65
     AssemblyCulture
    -0.64
     cherchés
    -0.64
    POSITIVE LOGITS
    :
    0.47
     :
    0.42
    ix
    0.41
    ::
    0.41
    id
    0.40
    pa
    0.38
     напо
    0.38
    ii
    0.38
    iw
    0.38
    ik
    0.37
    Activations Density 0.236%

    No Known Activations