© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 42335
    Prev
    Next
    INDEX
    Explanations

    terminology and descriptions related to the tongue and its characteristics in a medical context

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

    tongue diagnosis and appearance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    لينكات
    -0.50
    gdx
    -0.47
    CPtr
    -0.41
    évaluateur
    -0.39
    lencia
    -0.37
     Kershaw
    -0.37
    SceneManagement
    -0.36
    raisemb
    -0.35
    monton
    -0.35
    restes
    -0.35
    POSITIVE LOGITS
     tongue
    1.78
     tongues
    1.48
     Tongue
    1.41
    tongue
    1.38
    Tongue
    1.33
    舌
    1.25
     lengua
    1.15
     язык
    1.02
     língua
    1.00
     language
    0.98
    Activations Density 0.049%

    No Known Activations