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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1165
    Prev
    Next
    INDEX
    Explanations

    references to contrasting perspectives or alternatives

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

    phrases indicating alternative perspectives or approaches

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

    other way around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GrantedAuthority
    -0.65
    CppMethod
    -0.61
     {},
    
    -0.57
     defStyleAttr
    -0.57
    writeFieldEnd
    -0.55
     biotite
    -0.54
     Taktlose
    -0.52
     Materials
    -0.52
    ächtig
    -0.50
     bäst
    -0.49
    POSITIVE LOGITS
     coin
    1.02
     coins
    0.82
    coin
    0.76
     Coin
    0.75
     Coins
    0.67
    Coin
    0.65
     COIN
    0.60
    Coins
    0.57
     spectrum
    0.56
    coins
    0.55
    Activations Density 0.039%

    No Known Activations