Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3431
    Prev
    Next
    INDEX
    Explanations

    queries and their parameters in the context of programming or database querying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
    enumii
    -0.56
    basicConfig
    -0.53
     fullName
    -0.44
    abstractmethod
    -0.43
    سوب
    -0.43
     moitié
    -0.42
    createCell
    -0.42
     Hälfte
    -0.40
    一半
    -0.40
     getHeight
    -0.39
    POSITIVE LOGITS
     query
    2.67
    query
    2.47
     Query
    2.45
    Query
    2.28
     queries
    2.03
     QUERY
    2.02
    QUERY
    1.97
     Queries
    1.96
     querying
    1.84
     queried
    1.76
    Activations Density 0.122%

    No Known Activations