© 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. 11302
    Prev
    Next
    INDEX
    Explanations

    frequent mentions of the word "we" and its variations, indicating a collective or team-oriented sentiment

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

    first-person plural pronouns and verbs used in direct quotes or statements.

    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
    parsedMessage
    -0.88
    RenderAtEndOf
    -0.75
    GEBURTSDATUM
    -0.70
     myſelf
    -0.70
     faſt
    -0.68
     الرياضيه
    -0.66
     Anſ
    -0.64
    ſelves
    -0.63
     Theſe
    -0.61
     becauſe
    -0.61
    POSITIVE LOGITS
     kind
    0.53
     just
    0.52
     want
    0.46
     sort
    0.46
    就把
    0.45
     talked
    0.45
     Everybody
    0.41
     Just
    0.41
     talk
    0.41
     come
    0.41
    Activations Density 0.215%

    No Known Activations