Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16211
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

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

    Text after seemingly random characters or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    referred to in documents

    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
    DockStyle
    -0.73
    EndGlobalSection
    -0.72
    principalColumn
    -0.72
     فريبيس
    -0.69
    MarshalTo
    -0.68
    帖最后由
    -0.64
    外部リンク
    -0.64
     nahilalakip
    -0.63
     дописавши
    -0.60
    InSection
    -0.59
    POSITIVE LOGITS
    ftagPool
    0.59
     وتسجيلات
    0.59
    ="@+
    0.51
    omla
    0.49
     Réponses
    0.48
    בור
    0.47
    chanti
    0.47
     iArr
    0.46
    FileDescriptor
    0.45
    Референце
    0.45
    Activations Density 0.027%

    No Known Activations