© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3965
    Prev
    Next
    INDEX
    Explanations

    instances of the word "still" and its variations, indicating a focus on continuity or persistence in situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chaun
    -0.56
    Lucia
    -0.54
    ADELPHIA
    -0.54
    forName
    -0.53
     GBA
    -0.52
    CodeDom
    -0.52
    jura
    -0.50
     forskj
    -0.50
     substitutions
    -0.50
    løs
    -0.50
    POSITIVE LOGITS
    still
    1.08
    Still
    1.06
     still
    1.04
     Still
    1.02
     STILL
    0.95
    STILL
    0.92
    Todavía
    0.78
     ftill
    0.76
     masih
    0.75
     ainda
    0.73
    Activations Density 0.075%

    No Known Activations