© 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. 36-GEMMASCOPE-RES-16K
    6. 15794
    Prev
    Next
    INDEX
    Explanations

    frequent use of the term "etc" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.56
     MainAxisSize
    -0.53
    aarrggbb
    -0.53
    TagMode
    -0.49
    MigrationBuilder
    -0.47
     Houſe
    -0.47
    rivit
    -0.47
    CloseOperation
    -0.46
     Majefty
    -0.46
     ffilmiau
    -0.45
    POSITIVE LOGITS
    etera
    0.94
    々
    0.55
    eter
    0.50
    pp
    0.47
    etra
    0.46
     PP
    0.46
    etc
    0.44
    PP
    0.44
     pp
    0.43
     etc
    0.42
    Activations Density 0.138%

    No Known Activations