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. 3385
    Prev
    Next
    INDEX
    Explanations

    references to authors and their literary works

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

    Collection of short stories/essays

    np_acts-logits-general · gemini-2.0-flash

    short stories or essays

    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
     getchar
    -0.54
    IntoConstraints
    -0.50
    endcsname
    -0.48
    coder
    -0.48
     referenties
    -0.48
    auri
    -0.47
     Udemy
    -0.47
    IMPLEMENTATION
    -0.47
     Tempel
    -0.47
    addPreferredGap
    -0.46
    POSITIVE LOGITS
     short
    0.81
     nahilalakip
    0.78
    short
    0.74
    SHORT
    0.73
    Short
    0.71
    collected
    0.70
     essay
    0.69
     Short
    0.69
     essays
    0.68
     poems
    0.67
    Activations Density 0.247%

    No Known Activations