© 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. 31-GEMMASCOPE-RES-131K
    11. 21090
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to software, programming, or digital technology

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

    possessive and relative pronouns

    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
     herself
    -0.93
    herself
    -0.79
     koja
    -0.75
     została
    -0.74
     która
    -0.69
     miała
    -0.69
     která
    -0.69
     umana
    -0.68
     była
    -0.66
    Parcelize
    -0.66
    POSITIVE LOGITS
     himself
    0.63
     koji
    0.57
     који
    0.49
     his
    0.48
     ktorý
    0.48
     kuris
    0.45
    ът
    0.44
     который
    0.43
    his
    0.42
    彼が
    0.42
    Activations Density 0.065%

    No Known Activations