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. 10-GEMMASCOPE-RES-16K
    6. 4332
    Prev
    Next
    INDEX
    Explanations

    references to hydrogen and its compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Khe
    -0.74
     Garvey
    -0.69
     FAO
    -0.66
    deln
    -0.66
     Fila
    -0.66
     Plas
    -0.65
     Ramadhan
    -0.65
     vian
    -0.65
     Cebuano
    -0.64
     Warlock
    -0.64
    POSITIVE LOGITS
    hydrogen
    1.12
    Hydrogen
    1.05
     H
    1.04
     hydrogen
    0.98
    rH
    0.96
     Hydrogen
    0.92
     propOrder
    0.91
    mH
    0.90
     Wasserstoff
    0.86
    H
    0.84
    Activations Density 0.220%

    No Known Activations