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. 65396
    Prev
    Next
    INDEX
    Explanations

    numerical data points and coordinates

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

    latitude and longitude coordinates

    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
     informée
    -0.66
     estekak
    -0.63
    存于互联网档案馆
    -0.62
     arşivlendi
    -0.56
     <<<<<<<<<<<<<<
    -0.55
    énario
    -0.53
    :✨
    -0.53
    enderror
    -0.52
    initializeApp
    -0.51
    providedIn
    -0.50
    POSITIVE LOGITS
    LEncoder
    0.43
     nakalista
    0.42
     north
    0.37
    north
    0.35
     latitude
    0.34
     south
    0.33
    VIAF
    0.32
     onCreateView
    0.32
    centerY
    0.31
    5
    0.31
    Activations Density 0.017%

    No Known Activations