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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-GEMMASCOPE-RES-16K
    6. 9493
    Prev
    Next
    INDEX
    Explanations

    references to temporary files or data structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лю
    -0.75
    ero
    -0.74
    <em>
    -0.73
    DrawerToggle
    -0.72
     heart
    -0.72
     Saba
    -0.71
    4
    -0.70
    o
    -0.70
    ​
    -0.68
    endregion
    -0.68
    POSITIVE LOGITS
    tmp
    1.37
     tmp
    1.27
    Tmp
    1.15
    VIAF
    1.03
     fertiliser
    0.99
    SpringRunner
    0.96
    ympto
    0.95
    ConstraintMaker
    0.94
     TMP
    0.91
    daß
    0.90
    Activations Density 0.099%

    No Known Activations