© 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. 1814
    Prev
    Next
    INDEX
    Explanations

    actions involving physical interaction and conflict

    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
     record
    -0.50
     completo
    -0.48
     %).
    -0.47
    ncc
    -0.46
    source
    -0.46
     complete
    -0.46
    lija
    -0.45
    計
    -0.44
    もり
    -0.44
    eeq
    -0.42
    POSITIVE LOGITS
     المعيارى
    1.08
    LookAnd
    0.87
    PreferredItem
    0.80
    AddTagHelper
    0.75
    bootstrapcdn
    0.74
    tvguidetime
    0.74
     MenuView
    0.72
     Catalana
    0.71
     snippetHide
    0.71
     ExecuteAsync
    0.70
    Activations Density 0.209%

    No Known Activations