© 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 - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8103
    Prev
    Next
    INDEX
    Explanations

    terms related to file handling and data structures in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hoş
    -0.43
    Personensuche
    -0.42
    痉
    -0.42
    retudo
    -0.39
    mensa
    -0.37
    jooq
    -0.37
    kendo
    -0.37
     unterscheidet
    -0.37
    Aholisi
    -0.37
     capucha
    -0.36
    POSITIVE LOGITS
     file
    3.33
     File
    3.22
    File
    3.02
     FILE
    2.97
    file
    2.91
    FILE
    2.86
     files
    2.58
     getFile
    2.42
     Files
    2.38
    files
    2.28
    Activations Density 0.146%

    No Known Activations