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. 23-GEMMASCOPE-RES-16K
    6. 11991
    Prev
    Next
    INDEX
    Explanations

    instances of the word "miss" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndroidJUnit
    -0.68
    anyahu
    -0.65
    \}\\
    -0.62
    
    -0.60
    BagLayout
    -0.59
    はじめに
    -0.57
     ulang
    -0.56
    SUCCEEDED
    -0.56
    oredCriteria
    -0.55
    styleType
    -0.55
    POSITIVE LOGITS
     missed
    0.95
    Missed
    0.88
     missing
    0.86
     Missed
    0.86
     MISSING
    0.84
     misses
    0.83
    Missing
    0.82
     Missing
    0.81
    teps
    0.81
    tep
    0.80
    Activations Density 0.140%

    No Known Activations