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. 113247
    Prev
    Next
    INDEX
    Explanations

    references to chalcones and related chemical compounds

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

    chal compounds

    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
     pousser
    -0.42
     endforeach
    -0.42
    createServer
    -0.41
     republiky
    -0.40
     verksamhet
    -0.39
    reportWebVitals
    -0.39
     Gebrauch
    -0.38
    APORE
    -0.38
     Autorisations
    -0.37
    mybatisplus
    -0.36
    POSITIVE LOGITS
     Chal
    2.59
     chal
    2.36
    Chal
    2.30
    chal
    1.79
     Chalmers
    1.41
     chalet
    1.30
     Chaldean
    1.22
     Chalet
    1.17
     chall
    1.16
     Chall
    1.11
    Activations Density 0.008%

    No Known Activations