Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 24103
    Prev
    Next
    INDEX
    Explanations

    terms related to martial arts and combat sports

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

    martial artist fighting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Biôgrafia
    -0.47
    stüt
    -0.44
    NUMX
    -0.44
    lorette
    -0.43
     OMITBAD
    -0.42
    RAINT
    -0.41
     Fav
    -0.40
    Far
    -0.40
    kopp
    -0.40
     protoimpl
    -0.39
    POSITIVE LOGITS
     typelib
    0.50
    #+#
    0.45
     InputDecoration
    0.44
    createStatement
    0.41
     FetchType
    0.40
    LookAnd
    0.39
     AttributeSet
    0.39
     escova
    0.39
     láser
    0.38
     Karate
    0.37
    Activations Density 0.009%

    No Known Activations