© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 6669
    Prev
    Next
    INDEX
    Explanations

    references to directories in a file system context

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

    file directory paths

    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
     OnInit
    -0.45
    tslib
    -0.44
     Joaquín
    -0.42
    Hulk
    -0.41
     Joaquin
    -0.40
    Caitlin
    -0.40
     Celtics
    -0.40
    KommentareTeilen
    -0.38
    insics
    -0.38
     posX
    -0.38
    POSITIVE LOGITS
    Directory
    2.77
     Directory
    1.85
    directory
    1.56
    DIRECTORY
    1.48
     DIRECTORY
    1.34
     directory
    1.14
    Directories
    1.07
     directories
    0.84
    directories
    0.82
     directorio
    0.77
    Activations Density 0.003%

    No Known Activations