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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 2085
    Prev
    Next
    INDEX
    Explanations

    code snippets related to data insertion operations

    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
    AsUp
    -0.84
     חיצוניים
    -0.81
     bArr
    -0.78
    caccio
    -0.75
    rativa
    -0.71
    twig
    -0.68
    tinyos
    -0.67
     "@/
    -0.67
     blé
    -0.66
    flexDirection
    -0.66
    POSITIVE LOGITS
     Insert
    1.78
     insert
    1.74
     inserts
    1.73
     Inserts
    1.68
    Insert
    1.62
    insert
    1.52
     inserted
    1.52
     INSERT
    1.49
     inserting
    1.45
     Insertion
    1.44
    Activations Density 0.141%

    No Known Activations