Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 92893
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to programming interfaces and dynamic data structures

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

    NSDictionary json interface

    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
    __":
    
    -0.77
     Houſe
    -0.72
     Reſ
    -0.70
    ſelf
    -0.65
    providedIn
    -0.63
     ſtate
    -0.63
    ſelves
    -0.62
     betweenstory
    -0.62
     poffe
    -0.61
     houſe
    -0.61
    POSITIVE LOGITS
    dynamic
    0.69
     dynamic
    0.63
     Dynamic
    0.53
    Dynamic
    0.50
     uLocal
    0.47
     DYNAMIC
    0.45
     ceva
    0.45
    hintText
    0.43
     désolés
    0.42
    stdint
    0.41
    Activations Density 0.002%

    No Known Activations