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. 10441
    Prev
    Next
    INDEX
    Explanations

    references to file handling and I/O operations in programming

    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
    okovic
    -0.56
    lijst
    -0.54
    withIdentifier
    -0.51
    UserScript
    -0.49
     hornet
    -0.48
    ArgsConstructor
    -0.47
     stiffness
    -0.47
     Koenig
    -0.46
     Zimmerman
    -0.46
     EXPERIMENT
    -0.46
    POSITIVE LOGITS
     stream
    1.26
     Stream
    1.17
     streams
    1.14
    Stream
    1.12
    stream
    1.12
     STREAM
    1.04
     Streams
    1.04
     InputStream
    1.03
    STREAM
    1.02
    Streams
    0.99
    Activations Density 0.804%

    No Known Activations