© 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. 9-GEMMASCOPE-RES-16K
    11. 6820
    Prev
    Next
    INDEX
    Explanations

    references to system components and their relationships

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

    technical terminology related to system components and parts within larger structures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GenerationType
    -0.36
    HasColumnType
    -0.35
     igualdad
    -0.34
     eventdata
    -0.32
    Попис
    -0.31
    httphttps
    -0.31
     naveg
    -0.30
     userType
    -0.30
    сь
    -0.29
     Signalez
    -0.29
    POSITIVE LOGITS
     components
    1.12
     parts
    1.08
     Components
    1.00
    parts
    0.97
     initComponents
    0.94
    components
    0.92
    Components
    0.92
     Parts
    0.90
    Parts
    0.89
     COMPONENTS
    0.88
    Activations Density 0.787%

    No Known Activations