© 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. 20-GEMMASCOPE-RES-16K
    11. 8408
    Prev
    Next
    INDEX
    Explanations

    terms relating to individual actions and their dependence on conditions or specific details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ending in "ly" or "al"

    np_acts-logits-general · gemini-2.0-flash

    word beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NUMX
    -0.83
    %")
    -0.81
    )':
    -0.81
     ſta
    -0.81
     myſelf
    -0.80
     whoſe
    -0.79
     Forumite
    -0.79
    Aktualisiert
    -0.79
     auffi
    -0.79
     ſtand
    -0.78
    POSITIVE LOGITS
    开发者
    0.64
     capas
    0.60
    ĺ
    0.58
    <unused63>
    0.55
    ŕ
    0.55
    r
    0.52
    ual
    0.52
     immagin
    0.52
     dager
    0.51
     teh
    0.49
    Activations Density 0.484%

    No Known Activations