© 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. 24-GEMMASCOPE-RES-16K
    11. 8026
    Prev
    Next
    INDEX
    Explanations

    code snippets related to programming functions and their parameters

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

    Code diff indicators (@@ -[numbers]+)

    np_acts-logits-general · gemini-2.0-flash

    line numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ComponentModel
    -0.54
     [];
    -0.50
    <sup>
    -0.46
    。『
    -0.45
    *.
    -0.45
    argout
    -0.45
    %.
    -0.45
    %;
    -0.44
    外部リンク
    -0.44
     [].
    -0.43
    POSITIVE LOGITS
    TypedDataSet
    0.75
     line
    0.72
     Line
    0.72
     "..\..\..\
    0.70
     Zeile
    0.69
    脚注の使い方
    0.68
     "..\..\
    0.68
     LINE
    0.66
    Line
    0.62
    LINE
    0.61
    Activations Density 0.269%

    No Known Activations