Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4606
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking action or making decisions

    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
    tagHelper
    -0.60
     Autorizaciones
    -0.54
    日閲覧
    -0.51
    modb
    -0.46
    CppMethod
    -0.43
    
    -0.42
    出版年
    -0.42
    фраструк
    -0.42
     typelib
    -0.42
    basicConfig
    -0.42
    POSITIVE LOGITS
     risks
    0.68
    risks
    0.61
     leap
    0.60
     plunge
    0.57
     cue
    0.54
     risques
    0.54
     leaps
    0.54
     pendekatan
    0.53
     risk
    0.53
     riesgos
    0.52
    Activations Density 0.178%

    No Known Activations