© 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. 31-GEMMASCOPE-RES-131K
    6. 110783
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface interactions and data structures

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

    technical terms and programming

    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
    WebElementEntity
    -0.44
    ">//
    -0.43
    ιώ
    -0.43
     rent
    -0.41
    amaño
    -0.40
    ammen
    -0.39
     rents
    -0.38
    checkout
    -0.38
    abra
    -0.37
     Studium
    -0.36
    POSITIVE LOGITS
    الحياه
    0.56
    GEBURTSDATUM
    0.47
     protoimpl
    0.47
     المعيارى
    0.46
    BASEPATH
    0.45
    bootstrapcdn
    0.42
     Taktlose
    0.42
     productivo
    0.42
     CSRF
    0.41
    featureID
    0.40
    Activations Density 0.005%

    No Known Activations