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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 13828
    Prev
    Next
    INDEX
    Explanations

    content type headers and related metadata in various formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     >=",
    -0.52
     aikana
    -0.46
    reactstrap
    -0.46
    Vaata
    -0.45
    enfone
    -0.44
     насељу
    -0.43
     cerah
    -0.43
    _));
    -0.42
     kaldır
    -0.41
    BoxShadow
    -0.41
    POSITIVE LOGITS
    application
    1.44
     application
    1.39
    APPLICATION
    1.14
     APPLICATION
    1.09
     Application
    1.08
    Application
    1.05
     applications
    1.04
    applications
    0.99
    appli
    0.95
    MigrationBuilder
    0.95
    Activations Density 0.259%

    No Known Activations