© 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
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 14320
    Prev
    Next
    INDEX
    Explanations

    function calls related to file management in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ismer
    -0.35
     pengh
    -0.33
    Vanjske
    -0.33
    crollView
    -0.33
    NSDictionary
    -0.31
     escu
    -0.31
    NewReader
    -0.30
    Capítulo
    -0.30
     cuchar
    -0.30
     самой
    -0.30
    POSITIVE LOGITS
    './
    0.73
    "./
    0.73
     "./
    0.69
     './
    0.67
     ['./
    0.66
    Personensuche
    0.62
     Path
    0.60
     ProtoMessage
    0.59
    ("./
    0.59
     "../
    0.59
    Activations Density 0.254%

    No Known Activations