© 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. 1418
    Prev
    Next
    INDEX
    Explanations

    references to data types and their attributes, particularly related to size and format in coding contexts

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

    long/big Integer or Date

    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
     müſſen
    -0.79
    %)$
    -0.78
    IBOutlet
    -0.75
    <pad>
    -0.75
    <unused43>
    -0.74
     zwiſchen
    -0.74
    <unused41>
    -0.73
    <unused47>
    -0.73
    <unused16>
    -0.73
    <unused3>
    -0.73
    POSITIVE LOGITS
    Enough
    0.33
     genug
    0.33
     version
    0.30
     enough
    0.30
    ướ
    0.29
     slika
    0.27
     Enough
    0.27
     informes
    0.26
     pizarra
    0.26
    Adverten
    0.25
    Activations Density 0.039%

    No Known Activations