© 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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 5713
    Prev
    Next
    INDEX
    Explanations

    terms related to directories and file organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holdet
    -0.60
    fredo
    -0.56
    MockMvc
    -0.54
    initro
    -0.53
    impulan
    -0.53
     enjeux
    -0.52
    igra
    -0.52
     mourut
    -0.52
     coefficients
    -0.51
     useCallback
    -0.51
    POSITIVE LOGITS
    BeginContext
    0.92
     folds
    0.86
     Folding
    0.80
     folding
    0.79
     fold
    0.79
     folder
    0.77
    Folding
    0.70
     Federation
    0.69
    HtmlAttribute
    0.68
     directory
    0.67
    Activations Density 0.114%

    No Known Activations