Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 933
    Prev
    Next
    INDEX
    Explanations

    the word "still" and its variations, indicating a focus on continuity or persistence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wohnung
    -0.74
     Erie
    -0.67
    شة
    -0.66
    openConnection
    -0.66
    agreb
    -0.65
     Monfieur
    -0.65
     vectorielles
    -0.65
     sẻ
    -0.65
     Raton
    -0.64
    amazonaws
    -0.64
    POSITIVE LOGITS
     still
    3.17
    still
    2.99
     Still
    2.80
    Still
    2.78
    STILL
    2.68
     STILL
    2.60
     masih
    1.93
     todavía
    1.79
     ftill
    1.70
    依然
    1.68
    Activations Density 0.047%

    No Known Activations