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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 7083
    Prev
    Next
    INDEX
    Explanations

    references to "shadow" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    @[+][
    -0.36
    SourceChecksum
    -0.34
    canActivate
    -0.28
     AttributeSet
    -0.27
    math
    -0.27
    Trả
    -0.26
     impegn
    -0.26
    PREFERRED
    -0.25
    formatted
    -0.25
     الص
    -0.25
    POSITIVE LOGITS
    :✨
    1.01
     shadow
    0.86
    ########.
    0.78
    headers
    0.77
     Shadow
    0.75
     Schemes
    0.75
     Cursor
    0.73
     SHADOW
    0.73
     shadows
    0.72
    Shadow
    0.71
    Activations Density 0.120%

    No Known Activations