© 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. 11-GEMMASCOPE-RES-16K
    11. 12600
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "continue" related to ongoing actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TÉCN
    -0.49
    Sheikh
    -0.47
    artments
    -0.47
     blancas
    -0.47
     Berlín
    -0.47
     Grecs
    -0.46
     AIRCRAFT
    -0.46
     parís
    -0.46
     grecque
    -0.46
     Cádiz
    -0.43
    POSITIVE LOGITS
     continue
    1.43
    continue
    1.36
     Continues
    1.35
     Continue
    1.35
     continued
    1.35
     continues
    1.33
     continuing
    1.30
     continuance
    1.24
     Continued
    1.24
    Continue
    1.24
    Activations Density 0.133%

    No Known Activations