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. 12-GEMMASCOPE-RES-16K
    6. 2601
    Prev
    Next
    INDEX
    Explanations

    syntactical elements and structures typical in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ::::::::
    -0.50
     hu
    -0.49
    źć
    -0.47
     sguardo
    -0.47
     modelu
    -0.46
    ím
    -0.43
    ători
    -0.42
    ható
    -0.42
    Fors
    -0.42
    real
    -0.41
    POSITIVE LOGITS
    +#+#
    1.22
     AssemblyCulture
    1.06
     تضيفلها
    0.94
    AsUp
    0.88
    aarrggbb
    0.82
    хьтан
    0.76
    VIAF
    0.75
     ModelExpression
    0.75
    存于互联网档案馆
    0.72
    uxxxx
    0.71
    Activations Density 0.420%

    No Known Activations