© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 31-GEMMASCOPE-RES-16K
    11. 13165
    Prev
    Next
    INDEX
    Explanations

    instances of the word "still" and related concepts of ongoing processes or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "still" used to indicate continuity or persistence of an action or state.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     artık
    -0.81
     already
    -0.80
     again
    -0.74
     novamente
    -0.73
     nuevamente
    -0.73
     wiederum
    -0.72
    already
    -0.71
     ponownie
    -0.70
     다시
    -0.69
    Already
    -0.68
    POSITIVE LOGITS
     remains
    0.57
     remain
    0.54
     unchanged
    0.50
     stubbornly
    0.50
    下去
    0.49
     active
    0.49
     unab
    0.49
     retains
    0.49
    現役
    0.48
    remains
    0.47
    Activations Density 0.366%

    No Known Activations