© 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-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 14489
    Prev
    Next
    INDEX
    Explanations

    special start tokens indicating the beginning of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    …
    -0.66
    }{*}{
    -0.60
    numerusform
    -0.59
     …
    -0.59
    YMMV
    -0.57
     ‚
    -0.56
     ...
    -0.55
    ...
    -0.55
    ——————
    -0.50
     ‘
    -0.50
    POSITIVE LOGITS
    tagHelperRunner
    0.94
    DebuggerNonUser
    0.93
    ResumeLayout
    0.82
    TagHelper
    0.81
    شهاد
    0.81
    tagHelper
    0.74
    cshtml
    0.74
    WEBPACK
    0.74
    )";
    0.73
     nahilalakip
    0.72
    Activations Density 0.014%

    No Known Activations