© 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. 12860
    Prev
    Next
    INDEX
    Explanations

    terms related to conflict and caution within various contexts

    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
     AssemblyCompany
    -0.38
    {~
    -0.28
    робнее
    -0.27
     voork
    -0.27
     türlü
    -0.27
      
    -0.26
     Char
    -0.26
     Révolution
    -0.26
     traditional
    -0.25
     teneur
    -0.25
    POSITIVE LOGITS
     мәкал
    0.74
    ThroughAttribute
    0.66
     betweenstory
    0.63
     Bewußt
    0.61
     autorytatywna
    0.61
     slapping
    0.59
     Verhält
    0.59
    clearing
    0.58
     Einfluß
    0.58
    arangay
    0.57
    Activations Density 0.918%

    No Known Activations