© 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. 0-GEMMASCOPE-RES-16K
    6. 217
    Prev
    Next
    INDEX
    Explanations

    the presence of Japanese punctuation marks, particularly parentheses and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    van
    -0.61
    setCellValue
    -0.57
     InputDecoration
    -0.57
     cellpadding
    -0.56
     AssemblyCompany
    -0.54
     defaultstate
    -0.49
     bậc
    -0.47
    สุข
    -0.47
    ंदु
    -0.47
    Rüyada
    -0.47
    POSITIVE LOGITS
    ValueStyle
    0.69
    CloseOperation
    0.64
    ("")]
    0.64
    WAUKEE
    0.63
    NUMX
    0.62
     */;
    0.61
     ().
    0.61
    ]->
    0.61
    uxxxx
    0.60
    tvguidetime
    0.60
    Activations Density 0.227%

    No Known Activations