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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13923
    Prev
    Next
    INDEX
    Explanations

    key moments or actions within a sports context

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

    Code, non-English words, or unusual punctuation

    np_acts-logits-general · gemini-2.0-flash

    xml tags and punctuation

    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
     automatica
    -0.56
    #+#
    -0.56
     bersama
    -0.55
     popularidad
    -0.53
     teammate
    -0.51
     dirinya
    -0.50
     automaticamente
    -0.49
    hängigkeit
    -0.49
     automáticamente
    -0.49
     pronti
    -0.49
    POSITIVE LOGITS
    ScopeManager
    0.78
     Мексичка
    0.67
     الرياضيه
    0.65
    Fordítás
    0.57
     isNameExpr
    0.57
     चीज़ों
    0.56
     lenker
    0.55
     bpy
    0.54
    TypedDataSet
    0.54
     controlled
    0.53
    Activations Density 0.095%

    No Known Activations