© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 38612
    Prev
    Next
    INDEX
    Explanations

    occurrences of the access modifier "public" in the code

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

    public static declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parfaite
    -0.34
     Mary
    -0.31
     populaires
    -0.31
     humanidade
    -0.31
     publier
    -0.30
     pública
    -0.30
     sabido
    -0.30
     públicos
    -0.30
     critères
    -0.29
     publiques
    -0.29
    POSITIVE LOGITS
    Personendaten
    0.69
     fashiola
    0.61
    PropertyChanging
    0.61
    bootstrapcdn
    0.61
    ScopeManager
    0.60
     betweenstory
    0.59
     $_-
    0.59
    MenuInflater
    0.59
    iffance
    0.59
     ſelbſt
    0.58
    Activations Density 0.005%

    No Known Activations