© 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. 23-GEMMASCOPE-RES-16K
    6. 10156
    Prev
    Next
    INDEX
    Explanations

    specific names of authors and institutions in academic contexts

    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
     Référence
    -0.53
     Tobago
    -0.48
     grecque
    -0.48
    πως
    -0.47
     caviar
    -0.47
     forKey
    -0.46
    dze
    -0.46
     fuoco
    -0.46
     skär
    -0.46
    欢迎
    -0.46
    POSITIVE LOGITS
     Karnataka
    0.85
    UnusedPrivate
    0.81
     Bengaluru
    0.78
    calaure
    0.76
     Mysore
    0.73
     Kannada
    0.70
    homonymie
    0.69
     Bangalore
    0.69
     Vok
    0.68
    Karn
    0.67
    Activations Density 0.143%

    No Known Activations