© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 11634
    Prev
    Next
    INDEX
    Explanations

    sequence patterns and formatting symbols commonly used in programming and markup languages

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

    Markup or code-related tokens

    np_acts-logits-general · gemini-2.0-flash

    code field names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     T
    -0.47
     t
    -0.47
    <eos>
    -0.44
    ScopeManager
    -0.43
    loway
    -0.42
    プリング
    -0.41
    호
    -0.40
    u
    -0.40
    tés
    -0.39
     fuentes
    -0.39
    POSITIVE LOGITS
     HasFactory
    0.90
    Personendaten
    0.86
    elemField
    0.80
    ftagPool
    0.79
     Efq
    0.78
     CreateTagHelper
    0.77
     referenties
    0.74
    ConstraintMaker
    0.73
    UrlResolution
    0.72
    FieldBuilder
    0.69
    Activations Density 0.066%

    No Known Activations