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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15428
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to data transfer and memory management in programming contexts

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

    Code related to memory buffers and data transfer

    np_acts-logits-general · gemini-2.0-flash

    buffer transfer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URIComponent
    -0.39
     arquitect
    -0.37
     religione
    -0.35
     licencia
    -0.34
    rosin
    -0.33
    Демографія
    -0.33
     exit
    -0.32
     licencias
    -0.32
     Dominus
    -0.32
    logico
    -0.31
    POSITIVE LOGITS
     buffer
    0.90
     buffers
    0.84
     Buffer
    0.81
    buffer
    0.81
     BUFFER
    0.77
     Transfers
    0.76
     buffering
    0.76
     Transfer
    0.74
     transfer
    0.73
    Buffer
    0.73
    Activations Density 0.820%

    No Known Activations