© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14737
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols used in formal reasoning

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

    Mathematical or code-like expressions

    np_acts-logits-general · gemini-2.0-flash

    code and mathematics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    tagHelperRunner
    -0.72
     SwitchCompat
    -0.55
     snippetHide
    -0.53
    tvguidetime
    -0.53
    Viitteet
    -0.52
    matchCondition
    -0.52
    lillah
    -0.50
     @"/
    -0.49
     HasFactory
    -0.49
    bootstrapcdn
    -0.49
    POSITIVE LOGITS
    InjectAttribute
    0.57
    AccessorTable
    0.52
     avoient
    0.44
     nôtre
    0.43
    DoubleQuotes
    0.42
    UpInside
    0.42
     inscrição
    0.40
     étoit
    0.40
     poetas
    0.39
     armée
    0.39
    Activations Density 5.763%

    No Known Activations