© 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. 9-GEMMASCOPE-RES-131K
    6. 20148
    Prev
    Next
    INDEX
    Explanations

    references to toroidal structures in mathematical contexts

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

    torus orbits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isten
    -0.39
     Anderson
    -0.38
     Socialista
    -0.37
     Sanderson
    -0.36
    PARAM
    -0.36
    area
    -0.36
    semantics
    -0.35
    bode
    -0.35
    ComponentModel
    -0.34
    onk
    -0.34
    POSITIVE LOGITS
    Jwt
    2.70
     Jwt
    2.63
    jsonwebtoken
    1.00
     jwt
    0.98
     JWT
    0.96
    JWT
    0.90
     ModelExpression
    0.88
     Numerade
    0.78
    webtoken
    0.72
     SwitchCompat
    0.69
    Activations Density 0.001%

    No Known Activations