© 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. 15422
    Prev
    Next
    INDEX
    Explanations

    instances of communication or expressions of speech

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

    the verb "say" and related speech act constructions.

    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
     Partially
    -0.47
     Vac
    -0.43
     Den
    -0.42
    Den
    -0.39
     AN
    -0.39
    ^{\
    -0.38
     Mal
    -0.38
    どうやら
    -0.37
     Dra
    -0.37
     greatly
    -0.37
    POSITIVE LOGITS
     goodbye
    0.71
     EconPapers
    0.56
     hello
    0.56
    setContentView
    0.54
    PropertyChanging
    0.54
     lenker
    0.53
    goodbye
    0.52
     kasarigan
    0.52
     Réponses
    0.52
     שוליים
    0.52
    Activations Density 0.117%

    No Known Activations