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. 10515
    Prev
    Next
    INDEX
    Explanations

    statements and questions related to user inquiries or requests for help

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

    Follows questions or imperatives

    np_acts-logits-general · gemini-2.0-flash

    otherwise, alternatively, or questions

    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
     therefore
    -1.67
     Therefore
    -1.54
    Therefore
    -1.51
     Derfor
    -1.43
    Поэтому
    -1.41
    therefore
    -1.38
     hence
    -1.33
     Поэтому
    -1.30
    所以
    -1.23
     Hence
    -1.23
    POSITIVE LOGITS
     Preferably
    0.86
    Otherwise
    0.82
     preferably
    0.82
     Otherwise
    0.82
    MemoryWarning
    0.78
    お待ちしております
    0.75
     otherwise
    0.74
     altrimenti
    0.73
    Xna
    0.73
    Alternatively
    0.72
    Activations Density 0.304%

    No Known Activations