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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 12564
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -1.10
      
    -0.92
    ↵
    -0.75
    ...
    -0.70
     ...
    -0.69
     [
    -0.68
       
    -0.68
     (
    -0.66
        
    -0.66
    ↵↵
    -0.66
    POSITIVE LOGITS
     Efq
    1.63
    ſelves
    1.51
    ^(@)
    1.45
     Jefus
    1.44
     Majefty
    1.43
    ſelf
    1.43
    Personensuche
    1.41
     autorytatywna
    1.38
     myſelf
    1.37
     doubtnut
    1.33
    Activations Density 1.625%

    No Known Activations