© 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. 65291
    Prev
    Next
    INDEX
    Explanations

    terms related to structure, classification, and organization in scientific contexts

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

    mathematical and technical terms

    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
     nahilalakip
    -0.53
    principalTable
    -0.51
     surla
    -0.51
    Bronnen
    -0.50
    webElementXpaths
    -0.49
    ictwo
    -0.48
    Personendaten
    -0.44
    ंदीखरीदारी
    -0.44
    Autoritní
    -0.44
    DECREF
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    0.63
    GHIJKLM
    0.49
    들의
    0.39
    getBean
    0.39
     ſte
    0.39
     Gn
    0.38
    薨
    0.38
     Oll
    0.38
    يكب
    0.37
     âmes
    0.37
    Activations Density 1.704%

    No Known Activations