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. 1556
    Prev
    Next
    INDEX
    Explanations

    statistical terms and concepts related to data analysis and generalizations

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

    broad statements or groupings

    np_acts-logits-general · gemini-2.0-flash

    standard generalizations and populations

    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
    writeField
    -0.45
     defaultstate
    -0.44
    ngdoc
    -0.41
    GOTREF
    -0.40
    TintMode
    -0.40
     CanadaChoose
    -0.39
    findpost
    -0.38
    ménage
    -0.38
    enderror
    -0.37
    verifyException
    -0.37
    POSITIVE LOGITS
     disambiguazione
    0.50
     standard
    0.47
    標準
    0.45
     стандарт
    0.45
     estándar
    0.44
    标准
    0.43
     standaard
    0.43
     standart
    0.43
    ureusement
    0.42
     sagesse
    0.42
    Activations Density 0.673%

    No Known Activations