© 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. 11-GEMMASCOPE-RES-16K
    6. 4979
    Prev
    Next
    INDEX
    Explanations

    expressions of agreement or consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marin
    -0.50
     Thors
    -0.46
    portlet
    -0.46
     lud
    -0.45
    otechnology
    -0.45
     cast
    -0.43
     Lud
    -0.43
    Marin
    -0.43
     Flash
    -0.42
     holl
    -0.42
    POSITIVE LOGITS
     agree
    1.53
     Agree
    1.46
    Agree
    1.36
     agreeing
    1.36
    agree
    1.36
     agreed
    1.34
     agrees
    1.34
     agreement
    1.34
     Agreed
    1.30
    agreed
    1.28
    Activations Density 0.200%

    No Known Activations