© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 3955
    Prev
    Next
    INDEX
    Explanations

    references to specific Japanese entities or organizations

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

    Japanese words/company names

    np_acts-logits-general · gemini-2.0-flash

    Japanese company names and surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -0.35
     olmak
    -0.30
     olmayan
    -0.30
     needs
    -0.30
     skjø
    -0.29
     and
    -0.29
     olsa
    -0.29
     might
    -0.29
     Type
    -0.28
     
    -0.28
    POSITIVE LOGITS
    uxxxx
    1.23
    
    1.02
    httphttps
    0.90
     autorytatywna
    0.88
     ujednoznacz
    0.83
    ConstraintMaker
    0.77
    UserScript
    0.77
     nahilalakip
    0.77
     resourceCulture
    0.75
    点此举报
    0.73
    Activations Density 0.049%

    No Known Activations