© 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. 10864
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions or health issues

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

    medical terminology related to body parts and anatomical conditions.

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

    medical and anatomical measurements related to body parts and structural dimensions.

    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
    깐
    -0.45
    zama
    -0.40
    ubble
    -0.39
     Pockets
    -0.39
    DLE
    -0.38
    孀
    -0.38
    vss
    -0.38
    ächlich
    -0.37
    降
    -0.37
     AUSSI
    -0.36
    POSITIVE LOGITS
     corrective
    0.73
     correction
    0.69
     correcting
    0.67
     straighten
    0.65
     straightening
    0.65
     Correction
    0.65
     corriger
    0.64
     corregir
    0.63
     Corre
    0.63
     corrected
    0.62
    Activations Density 0.306%

    No Known Activations