© 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. 11951
    Prev
    Next
    INDEX
    Explanations

    mentions of medical conditions or treatments and their implications

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

    sentences or clauses involving verbs like "said", "explained", "told", "claimed", or other reporting/speaking verbs.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    phrases describing someone taking on or assuming a role or position.

    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
    httphttps
    -0.73
    setVerticalGroup
    -0.73
    MLLoader
    -0.67
    IntoConstraints
    -0.66
    principalTable
    -0.65
    RegressionTest
    -0.65
    TagMode
    -0.64
    IBOutlet
    -0.64
    OGND
    -0.63
    __(/*!
    -0.63
    POSITIVE LOGITS
    该
    0.71
    該
    0.68
     该
    0.51
     it
    0.43
     dicha
    0.40
     tersebut
    0.36
     saken
    0.34
    同
    0.33
     said
    0.30
     dicho
    0.30
    Activations Density 1.040%

    No Known Activations