© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1301
    Prev
    Next
    INDEX
    Explanations

    phrases and references related to organizational or event details

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

    dates, time periods, or festivals

    np_acts-logits-general · gemini-2.0-flash

    film festival

    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
     дописавши
    -0.69
    :✨
    -0.65
    MLLoader
    -0.62
     CreateTagHelper
    -0.62
    LookAnd
    -0.62
     мәкал
    -0.58
    SequentialGroup
    -0.56
    zzleHttp
    -0.56
     unknownFields
    -0.53
     vectorielle
    -0.52
    POSITIVE LOGITS
    当时
    0.45
    當時
    0.41
    当时的
    0.38
    那时候
    0.35
    那时
    0.35
    ("]");
    0.34
     bija
    0.32
    Below
    0.31
     damaligen
    0.31
    scoped
    0.30
    Activations Density 1.215%

    No Known Activations