© 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. 37-GEMMASCOPE-RES-16K
    6. 5580
    Prev
    Next
    INDEX
    Explanations

    references to the action of pulling in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zzleHttp
    -0.52
    CodeAttribute
    -0.46
     Италијани
    -0.46
    RestTemplate
    -0.45
    APIView
    -0.45
    propTypes
    -0.44
     
    -0.43
    Derbyniad
    -0.42
    клопе
    -0.41
    Mere
    -0.39
    POSITIVE LOGITS
     trigger
    0.63
     plug
    0.62
    Pull
    0.61
     Pull
    0.60
     pulled
    0.60
     PULL
    0.59
     Pulling
    0.58
     pull
    0.57
    PULL
    0.57
     apart
    0.57
    Activations Density 0.141%

    No Known Activations