© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 16649
    Prev
    Next
    INDEX
    Explanations

    discussions around traditional skills and their relevance in contemporary society

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

    necessity and importance

    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
    tualmente
    -0.34
    enquête
    -0.33
     Nachteile
    -0.32
     antworten
    -0.31
     kämpfen
    -0.31
     Silhouette
    -0.31
    theoremstyle
    -0.31
     expecting
    -0.31
    écnicas
    -0.29
    şk
    -0.29
    POSITIVE LOGITS
     doInBackground
    0.65
     transfieras
    0.65
     disambiguazione
    0.62
    OGND
    0.62
    parsedMessage
    0.61
    providedIn
    0.59
     CanadaChoose
    0.58
    Jîn
    0.57
     <<<<<<<<<<<<<<
    0.56
     defaultstate
    0.56
    Activations Density 0.067%

    No Known Activations