© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 12152
    Prev
    Next
    INDEX
    Explanations

    underscore-prefixed identifiers and related patterns in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -1.15
    ConstraintMaker
    -1.06
    ReusableCell
    -1.03
    InjectAttribute
    -0.97
     AssemblyVersion
    -0.95
     MainAxisSize
    -0.95
    AddHtmlAttribute
    -0.93
    contentLoaded
    -0.93
    UserScript
    -0.93
    GraphicsUnit
    -0.92
    POSITIVE LOGITS
    Pyx
    0.63
    området
    0.49
    Internal
    0.49
     reverse
    0.47
    The
    0.47
    recursive
    0.46
     internal
    0.46
     Reverse
    0.45
    getNext
    0.44
    CURS
    0.44
    Activations Density 0.282%

    No Known Activations