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. 8-GEMMASCOPE-RES-16K
    6. 15127
    Prev
    Next
    INDEX
    Explanations

    references to occurrences or instances within a structured context, such as "block" or "level"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     payé
    -0.79
    %)$
    -0.75
    stdarg
    -0.73
    zczegól
    -0.72
     musicales
    -0.71
    HttpFoundation
    -0.71
     Ory
    -0.71
     bå
    -0.71
     sauvage
    -0.70
    Cuáles
    -0.70
    POSITIVE LOGITS
     BLOCK
    1.98
     blocks
    1.93
     Block
    1.91
     block
    1.88
    block
    1.86
    BLOCK
    1.85
     Blocks
    1.83
    Block
    1.78
    blocks
    1.77
    Blocks
    1.65
    Activations Density 0.037%

    No Known Activations