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. 22-GEMMASCOPE-RES-16K
    6. 10546
    Prev
    Next
    INDEX
    Explanations

    information related to food sourcing and dietary preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "and," "of," or parentheses

    np_acts-logits-general · gemini-2.0-flash

    cheese and pickle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olv
    -0.56
    তথ্যসূত্র
    -0.54
    Personensuche
    -0.52
    קישורים
    -0.50
    ">//
    -0.49
     gæ
    -0.49
     clerk
    -0.49
    ThroughAttribute
    -0.48
     neceff
    -0.48
     strategis
    -0.46
    POSITIVE LOGITS
    
    0.62
     pensioners
    0.59
    proper
    0.57
     prawn
    0.56
     posh
    0.56
    RRP
    0.55
     Cypri
    0.55
     Punj
    0.53
    SourceChecksum
    0.52
     reared
    0.51
    Activations Density 0.187%

    No Known Activations