© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 93154
    Prev
    Next
    INDEX
    Explanations

    words and terms related to the concept of "funk."

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

    funky, funk, chunky, Funk, Dunkin

    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
     disambiguazione
    -0.76
    ScopeManager
    -0.72
    Personendaten
    -0.68
     CreateTagHelper
    -0.66
    setVerticalGroup
    -0.65
     ſont
    -0.59
     esternos
    -0.57
    LLocation
    -0.56
    ImageContext
    -0.54
    MessageTagHelper
    -0.54
    POSITIVE LOGITS
    Funky
    0.52
     Funky
    0.52
     funky
    0.47
    funky
    0.44
    Funk
    0.41
     Funk
    0.38
     rock
    0.37
     ugly
    0.37
    junk
    0.34
     prevención
    0.34
    Activations Density 0.003%

    No Known Activations