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. 5793
    Prev
    Next
    INDEX
    Explanations

    terms related to verification and privacy agreements

    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
    orologio
    -0.57
    esterno
    -0.53
    HasColumnType
    -0.52
     disponibilités
    -0.51
    GeneratedMessage
    -0.51
    OrBuilder
    -0.51
     transfieras
    -0.50
     oiseaux
    -0.49
     Wrench
    -0.49
    Fitment
    -0.49
    POSITIVE LOGITS
    ScopeManager
    0.56
    رشف
    0.55
    chrome
    0.55
    utory
    0.50
    trip
    0.49
    '}>
    0.48
    wound
    0.48
     trip
    0.48
    impin
    0.48
    ssus
    0.47
    Activations Density 0.018%

    No Known Activations