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. 9-GEMMASCOPE-RES-16K
    6. 1557
    Prev
    Next
    INDEX
    Explanations

    class and function definitions in programming-related text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.85
    principalColumn
    -0.75
    AndEndTag
    -0.68
     Territorial
    -0.66
    jsonwebtoken
    -0.64
    <bos>
    -0.64
    justed
    -0.64
    kháu
    -0.64
    évaluateur
    -0.63
     réflex
    -0.61
    POSITIVE LOGITS
    坞
    0.56
    WebVitals
    0.53
     method
    0.44
    JdbcTemplate
    0.41
     rzecz
    0.40
    солю
    0.38
     paramInt
    0.38
    ödie
    0.38
    defn
    0.38
    Przypisy
    0.38
    Activations Density 0.174%

    No Known Activations