© 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. 12804
    Prev
    Next
    INDEX
    Explanations

    key functions and method signatures related to API requests and data handling in programming

    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
    ，“
    -0.61
    󠁢
    -0.58
     transfieras
    -0.58
    onedDateTime
    -0.56
     ("%
    -0.56
    ，「
    -0.56
    انتهای
    -0.56
    ftagPool
    -0.54
     "");
    -0.54
    ResumeLayout
    -0.54
    POSITIVE LOGITS
    (
    0.60
    (){
    0.58
    (){}
    0.54
    ()
    0.52
    (){
    0.49
    </h2>
    0.47
    ():
    0.46
    </b>
    0.45
     (
    0.45
    …
    0.41
    Activations Density 0.273%

    No Known Activations