© 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. 20-GEMMASCOPE-RES-131K
    6. 46693
    Prev
    Next
    INDEX
    Explanations

    terms related to categories and classifications, particularly pertaining to surnames, authors, and biological or scientific classifications

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

    birth and citation contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beant
    -0.34
    whatever
    -0.33
    ble
    -0.32
     whatever
    -0.32
    KommentareTeilen
    -0.31
     stolz
    -0.31
    blah
    -0.31
    disposed
    -0.30
     Initialized
    -0.30
    com
    -0.30
    POSITIVE LOGITS
    Personendaten
    0.88
    MessageOf
    0.65
    Numerade
    0.64
     esternos
    0.62
     transférez
    0.59
    \{\\
    0.57
    
    0.57
    󠁣
    0.57
    Viited
    0.57
     saites
    0.56
    Activations Density 0.000%

    No Known Activations