© 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
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12791
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and relationships in the context of theoretical frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.86
    UnusedPrivate
    -0.83
    
    -0.76
    BufferException
    -0.75
    TypedDataSet
    -0.72
     MainAxisSize
    -0.69
    elemField
    -0.69
    ="@+
    -0.69
     snippetHide
    -0.69
     defaultstate
    -0.69
    POSITIVE LOGITS
     respect
    0.67
     assuming
    0.61
     relative
    0.56
     modulo
    0.54
     everywhere
    0.52
    respect
    0.52
     irrespective
    0.48
     when
    0.47
     respecte
    0.47
     under
    0.47
    Activations Density 2.552%

    No Known Activations