© 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 EvalsExportsinterp-engineNEWAPI 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. 3332
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and references to people in a conversational context

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

    pronouns and verbs used in direct speech or quotations, particularly when someone is speaking or being quoted.

    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
     '\\;'
    -0.80
     فريبيس
    -0.66
    __":
    -0.64
    CppMethod
    -0.63
    uxxxx
    -0.57
    WithIOException
    -0.57
    bootstrapcdn
    -0.56
    parsedMessage
    -0.56
    oa̍t
    -0.56
    IsMutable
    -0.56
    POSITIVE LOGITS
     wrote
    0.72
     says
    0.64
     said
    0.63
     concluded
    0.61
     told
    0.58
     stated
    0.54
     tweeted
    0.53
     exclaimed
    0.53
     writes
    0.52
     conclude
    0.50
    Activations Density 0.069%

    No Known Activations