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. 21-GEMMASCOPE-RES-16K
    6. 15092
    Prev
    Next
    INDEX
    Explanations

    references to data structures and parameters in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    ']):
    -1.24
    '):
    
    -1.19
    ']:
    -1.17
    '])->
    -1.13
    '],
    
    -1.11
    ()){
    
    -1.09
    '){
    
    -1.08
    ')):
    -1.08
    "]:
    -1.07
    '}>
    -1.07
    POSITIVE LOGITS
    ↵
    1.28
    ↵↵↵
    1.04
    ↵↵
    0.80
     purpoſe
    0.69
    </blockquote>
    0.68
    ↵↵↵↵↵
    0.67
     himſelf
    0.67
    ↵↵↵↵
    0.66
    <eos>
    0.63
     Jefus
    0.60
    Activations Density 0.248%

    No Known Activations