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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 219
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to entities or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.61
    delwed
    -0.55
     برانيه
    -0.54
     nahilalakip
    -0.51
     indígen
    -0.49
    Portail
    -0.48
     الرياضيه
    -0.48
    
    -0.46
     occaf
    -0.45
    AutoScaleMode
    -0.45
    POSITIVE LOGITS
    BeginContext
    0.43
    <?
    0.38
    acies
    0.38
    اریخ
    0.36
     compró
    0.35
     scu
    0.34
    americas
    0.34
     bVar
    0.34
    EMY
    0.34
     stel
    0.34
    Activations Density 0.118%

    No Known Activations