© 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. 8-GEMMASCOPE-RES-16K
    11. 11054
    Prev
    Next
    INDEX
    Explanations

    items related to the concept of "listing" or "grouping" in data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.66
    execSQL
    -0.66
     ""));
    -0.64
     ")");
    -0.64
     "");
    -0.64
    ()]
    -0.62
    )])
    -0.62
     "";
    -0.60
    OOTDTY
    -0.60
     "
    -0.60
    POSITIVE LOGITS
    脚注の使い方
    1.01
    setDo
    0.82
    Παραπομπές
    0.74
    блиоте
    0.74
    mapTo
    0.73
    gatsby
    0.72
     Sigism
    0.71
    findBy
    0.71
    ########.
    0.70
     Byr
    0.70
    Activations Density 0.089%

    No Known Activations