© 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 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. 15244
    Prev
    Next
    INDEX
    Explanations

    questions and affirmations related to identity or specific attributes

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

    contrasting clauses or statements introduced by "whether" or "it".

    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
     $_"
    -0.54
    CopyWith
    -0.49
     queſta
    -0.46
    mule
    -0.46
     ſind
    -0.45
     $_(
    -0.45
    ":[{
    -0.44
    AISSEE
    -0.44
    =-=-
    -0.44
     parseFrom
    -0.43
    POSITIVE LOGITS
     is
    0.99
     là
    0.91
     ialah
    0.85
    คือ
    0.85
    เป็น
    0.84
     adalah
    0.84
     является
    0.71
    是
    0.68
    のは
    0.65
    adalah
    0.64
    Activations Density 0.982%

    No Known Activations