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. 5-GEMMASCOPE-RES-16K
    6. 7533
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to device communication interfaces, particularly for serial ports and user input devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.92
     onPostExecute
    -0.80
     estekak
    -0.79
    ValueStyle
    -0.77
     Normdatei
    -0.77
     autorytatywna
    -0.75
    addCriterion
    -0.75
    脚注の使い方
    -0.72
     inappropriés
    -0.71
    CGRectMake
    -0.71
    POSITIVE LOGITS
     output
    0.94
     input
    0.89
    output
    0.84
    Output
    0.83
     inputs
    0.77
    stdout
    0.77
    input
    0.73
     Output
    0.73
    Input
    0.73
     stdout
    0.70
    Activations Density 0.446%

    No Known Activations