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. 24-GEMMASCOPE-RES-131K
    6. 1030
    Prev
    Next
    INDEX
    Explanations

    software or programming-related terms

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

    tablix at or Report Server

    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_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.51
    あれば
    -0.39
    OGND
    -0.38
    getSystemService
    -0.34
     olsun
    -0.34
     &___
    -0.33
     samping
    -0.31
    geführten
    -0.31
    Options
    -0.31
    chooser
    -0.31
    POSITIVE LOGITS
    XtraReports
    1.37
    xrLabel
    0.80
    xrTableCell
    0.77
    󠁣
    0.53
     transfieras
    0.52
    Tracce
    0.52
     للمعارف
    0.51
     imprim
    0.50
    
    0.49
    webElementXpaths
    0.48
    Activations Density 0.000%

    No Known Activations