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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1272
    Prev
    Next
    INDEX
    Explanations

    instructions related to baking or cooking processes

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

    dough or batter recipes

    np_acts-logits-general · gemini-2.0-flash

    making dough and batter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.59
    quelize
    -0.43
    AddTagHelper
    -0.42
    HCR
    -0.41
    ATURA
    -0.40
     special
    -0.40
    codecSelfer
    -0.40
     Klick
    -0.40
     Reverso
    -0.40
    évaluateur
    -0.39
    POSITIVE LOGITS
     ujednoznacz
    0.48
     الرياضيه
    0.46
    ArgumentParser
    0.46
    Geplaatst
    0.41
     dough
    0.41
    totalSupply
    0.40
    Хьажоргаш
    0.40
    IsMutable
    0.40
     Grundstück
    0.39
    Diweddarwch
    0.38
    Activations Density 0.315%

    No Known Activations