© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9023
    Prev
    Next
    INDEX
    Explanations

    actions involving cutting or slicing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     state
    -0.50
    STATE
    -0.47
     status
    -0.46
     getState
    -0.46
    estatus
    -0.45
    InstanceState
    -0.45
    atoare
    -0.44
     estado
    -0.43
     State
    -0.43
     Eub
    -0.42
    POSITIVE LOGITS
     Cutting
    1.08
    Cutting
    1.07
     cut
    1.01
     cutting
    1.00
    cuts
    0.99
    cutting
    0.97
    Cuts
    0.96
     CUT
    0.95
     cuts
    0.95
    cut
    0.95
    Activations Density 0.413%

    No Known Activations