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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 10484
    Prev
    Next
    INDEX
    Explanations

    the presence of different types of special characters and formatting symbols

    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
    IUrlHelper
    -0.90
    MigrationBuilder
    -0.85
     Roskov
    -0.84
    RegressionTest
    -0.84
    RenderAtEndOf
    -0.77
     مرئيه
    -0.73
     الحره
    -0.72
     Monfieur
    -0.71
    ctools
    -0.71
     виправивши
    -0.71
    POSITIVE LOGITS
     truly
    0.60
     really
    0.57
    textit
    0.57
     absolutely
    0.53
    er
    0.52
    <i>
    0.52
     wirklich
    0.52
     literally
    0.50
     ‘
    0.50
    <em>
    0.47
    Activations Density 0.223%

    No Known Activations