© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 647
    Prev
    Next
    INDEX
    Explanations

    connections involving the concept of boundaries or limits

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

    phrases related to mathematical or statistical bounds and comparisons

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

    preposition of origin or direction

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    expandindo
    -0.65
    writeFieldEnd
    -0.47
    moveToFirst
    -0.46
    WebServlet
    -0.45
    figsize
    -0.42
    tahui
    -0.42
     numerus
    -0.42
     maxim
    -0.42
    esgue
    -0.41
    pagestyle
    -0.40
    POSITIVE LOGITS
     from
    1.87
    from
    1.53
     From
    1.45
     FROM
    1.42
    From
    1.36
     từ
    1.36
     desde
    1.34
    FROM
    1.27
    从
    1.25
     dari
    1.22
    Activations Density 0.203%

    No Known Activations