© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 13010
    Prev
    Next
    INDEX
    Explanations

    programming code and syntax elements

    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
    MigrationBuilder
    -0.67
    PyExc
    -0.60
    脚注の使い方
    -0.59
    KommentareTeilen
    -0.54
    findpost
    -0.53
     demografica
    -0.52
    BeginInit
    -0.52
     ddelweddau
    -0.51
     estekak
    -0.50
    RTSC
    -0.50
    POSITIVE LOGITS
     hot
    0.35
     argint
    0.34
     goods
    0.34
     publier
    0.34
     méri
    0.33
    iphery
    0.33
    Focus
    0.33
     mío
    0.32
     Goods
    0.32
     saya
    0.31
    Activations Density 0.058%

    No Known Activations