Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12941
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names throughout the text

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

    personal names

    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
     kasarigan
    -0.65
    ValueStyle
    -0.61
    :✨
    -0.58
    Autoritní
    -0.55
    bootstrapcdn
    -0.53
    OGND
    -0.52
    IFICATE
    -0.52
    arina
    -0.50
    uxxxx
    -0.50
    ipients
    -0.50
    POSITIVE LOGITS
    ędziesz
    0.37
     himself
    0.35
     zufolge
    0.35
    ’
    0.34
    '
    0.34
     will
    0.32
     getroffen
    0.31
     who
    0.31
     RSSSF
    0.31
     chofe
    0.31
    Activations Density 0.026%

    No Known Activations