© 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. 3-GEMMASCOPE-RES-16K
    11. 12195
    Prev
    Next
    INDEX
    Explanations

    repeating patterns or sequences in code-like structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.69
     Мексичка
    -0.66
    <bos>
    -0.54
     AssemblyVersion
    -0.53
     فريبيس
    -0.52
     AssemblyCulture
    -0.50
     naselje
    -0.49
    idão
    -0.48
    matchCondition
    -0.48
     NUKAT
    -0.48
    POSITIVE LOGITS
     الحره
    0.73
     Réponses
    0.65
    tonode
    0.63
    formis
    0.62
    ็จ
    0.62
    ativement
    0.59
    PerformLayout
    0.58
     nahilalakip
    0.58
    WSGI
    0.58
    pendenti
    0.57
    Activations Density 0.048%

    No Known Activations