© 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
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 579
    Prev
    Next
    INDEX
    Explanations

    references to file paths and errors related to file operations

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

    filepath, FBS final, jeopardized, Tierney's

    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
    ")));
    
    -0.57
    Slf
    -0.53
    setAll
    -0.50
     Haller
    -0.49
    on
    -0.48
    Store
    -0.47
    mathcal
    -0.46
    l
    -0.44
    󠁮
    -0.43
    ']))
    
    -0.43
    POSITIVE LOGITS
     filePath
    0.91
    FilePath
    0.79
    filePath
    0.77
     وتسجيلات
    0.66
    filepath
    0.59
    Diwedd
    0.59
    phemy
    0.59
     flèche
    0.58
    gucigalpa
    0.57
    quoise
    0.57
    Activations Density 0.005%

    No Known Activations