© 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. 3-GEMMASCOPE-RES-16K
    6. 1882
    Prev
    Next
    INDEX
    Explanations

    names of individuals and places, particularly in a historical or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    initComponents
    -0.60
    彡
    -0.57
    textTheme
    -0.56
    xymatrix
    -0.52
     GoogleFonts
    -0.52
    newtheorem
    -0.51
    期刊论文
    -0.51
    autoconfigure
    -0.51
    brainly
    -0.49
    pædia
    -0.49
    POSITIVE LOGITS
    PreferredItem
    0.92
     TextAppearance
    0.70
    TagHelper
    0.68
    aarrggbb
    0.68
    CloseOperation
    0.67
    expandindo
    0.65
    riwal
    0.65
    туга
    0.61
     =>'
    0.60
    UrlResolution
    0.59
    Activations Density 1.517%

    No Known Activations