© 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. 20-GEMMASCOPE-RES-16K
    6. 7802
    Prev
    Next
    INDEX
    Explanations

    CSS style properties and their values

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

    Code snippets and formatting elements

    np_acts-logits-general · gemini-2.0-flash

    number followed by each

    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
    .
    -0.63
    ,
    -0.56
    !
    -0.52
    rungsseite
    -0.51
    liferay
    -0.48
    /
    -0.46
    _
    -0.45
    LEncoder
    -0.43
     django
    -0.43
    '
    -0.42
    POSITIVE LOGITS
    ')}}">
    0.78
     inherit
    0.77
    Geplaatst
    0.75
     olympique
    0.74
    |}{$
    0.72
    )$_
    0.71
    inherit
    0.71
     nahilalakip
    0.70
    */;
    0.70
    "])
    
    0.69
    Activations Density 0.086%

    No Known Activations