© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13763
    Prev
    Next
    INDEX
    Explanations

    questions that involve the words "is" and "does."

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

    interrogative structures, particularly questions beginning with "Does" or "Why".

    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
     dieselben
    -0.60
     những
    -0.54
     diejenigen
    -0.53
     רבים
    -0.50
     jsme
    -0.50
     många
    -0.49
     beide
    -0.47
     многие
    -0.46
    śmy
    -0.46
     we
    -0.46
    POSITIVE LOGITS
     it
    0.67
     there
    0.51
     CanadaChoose
    0.50
     anyone
    0.48
     this
    0.47
    tete
    0.47
    ours
    0.46
    ंदीखरीदारी
    0.46
     BorderSide
    0.46
     Eing
    0.45
    Activations Density 0.280%

    No Known Activations