© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3544
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and literature

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

    Follows "Q:" or parentheses

    np_acts-logits-general · gemini-2.0-flash

    Q:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     again
    -0.52
    tolist
    -0.48
    PYX
    -0.47
    aarrggbb
    -0.47
     obje
    -0.47
    چی
    -0.45
     걸
    -0.44
    vstack
    -0.44
    onTap
    -0.43
     offering
    -0.43
    POSITIVE LOGITS
     BoxFit
    0.88
     unpublished
    0.87
    unpublished
    0.68
     Мексичка
    0.62
     undated
    0.61
     الرياضيه
    0.61
     personnelle
    0.61
     passim
    0.61
    appé
    0.60
    __':
    
    0.60
    Activations Density 0.346%

    No Known Activations