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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 5676
    Prev
    Next
    INDEX
    Explanations

    code and programming-related elements in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reading
    -0.85
     Reading
    -0.72
    BitmapFactory
    -0.71
     readings
    -0.70
     lettura
    -0.70
    imread
    -0.69
     read
    -0.69
    Reading
    -0.69
    reading
    -0.67
    fread
    -0.64
    POSITIVE LOGITS
     output
    1.29
     Output
    1.24
    output
    1.24
    writer
    1.23
    Writer
    1.17
     write
    1.17
     writer
    1.15
    Output
    1.14
    write
    1.13
     Writer
    1.12
    Activations Density 0.458%

    No Known Activations