© 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. 13141
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and parentheses in the text

    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
     jahr
    -0.54
     comunque
    -0.51
    urlpatterns
    -0.49
     intptr
    -0.49
    oldt
    -0.49
     invece
    -0.47
    !("{
    -0.46
    stdc
    -0.46
     GenerationType
    -0.46
     JpaRepository
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.78
     "..\..\..\
    0.70
    matchCondition
    0.69
    )__
    0.65
    migrationBuilder
    0.64
    #
    0.63
    isburg
    0.63
    DockStyle
    0.61
     useCallback
    0.60
     ainfi
    0.59
    Activations Density 0.171%

    No Known Activations