© 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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 15080
    Prev
    Next
    INDEX
    Explanations

    the word "still" and its variants, indicating a sense of continuation or persistence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    offsetof
    -0.57
    APON
    -0.56
    anada
    -0.56
    verein
    -0.54
    izione
    -0.53
     Racine
    -0.53
     Familienname
    -0.52
    ῇ
    -0.52
    ogaster
    -0.51
     asma
    -0.50
    POSITIVE LOGITS
     still
    4.71
    still
    4.38
    Still
    4.01
     Still
    3.98
     STILL
    3.62
    STILL
    3.52
     masih
    2.87
     ftill
    2.81
     todavía
    2.72
     fortfarande
    2.63
    Activations Density 0.051%

    No Known Activations