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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 13273
    Prev
    Next
    INDEX
    Explanations

    verbs related to movement or transitioning from one place or state to another

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     onError
    -0.46
     Bantam
    -0.46
     BeautifulSoup
    -0.44
    onError
    -0.43
     whiteColor
    -0.43
    isNotNull
    -0.43
    preventDefault
    -0.40
     ***!
    -0.40
    wantErr
    -0.40
     Consortium
    -0.39
    POSITIVE LOGITS
     Move
    1.26
     move
    1.26
    Move
    1.24
    move
    1.23
     MOVE
    1.21
     moved
    1.16
    Moved
    1.15
    MOVE
    1.14
    moved
    1.13
     Moves
    1.12
    Activations Density 0.174%

    No Known Activations