© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 117006
    Prev
    Next
    INDEX
    Explanations

    references to utility classes and functions in code

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

    utility and test code

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     disambiguazione
    -0.65
     nahilalakip
    -0.56
    rungsseite
    -0.56
    tagHelperRunner
    -0.46
    SharedCtor
    -0.45
     оригіналу
    -0.45
    EndInit
    -0.45
     poffible
    -0.45
    ésultat
    -0.45
    SBATCH
    -0.45
    POSITIVE LOGITS
    reamble
    0.44
    __*/
    0.43
    IEA
    0.42
    CELLANEOUS
    0.42
    AllAfrica
    0.40
    runApp
    0.39
     太郎
    0.39
     Agre
    0.39
    加州
    0.39
     itse
    0.38
    Activations Density 0.062%

    No Known Activations