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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 130018
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and configurations

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

    configuration parameters or settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     []*
    -0.44
     мәкал
    -0.43
    IVEREF
    -0.42
     Chwiliwch
    -0.41
    httphttps
    -0.40
     ض
    -0.39
    weightedMode
    -0.37
     ويكيپيديا
    -0.37
    цездатний
    -0.36
    addAll
    -0.36
    POSITIVE LOGITS
     parameter
    0.68
     settings
    0.62
     value
    0.59
     configuration
    0.58
     propOrder
    0.57
    parameter
    0.56
     Configuration
    0.56
     Settings
    0.56
     config
    0.55
    配置
    0.55
    Activations Density 0.032%

    No Known Activations