© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2395
    Prev
    Next
    INDEX
    Explanations

    articles and determiners in sentences

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

    phrases that start with "it is a" or "it is an", often introducing a technical or formal statement about an object, method, or concept.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    ConfigureAwait
    -0.39
     siquiera
    -0.38
     esimerkiksi
    -0.37
    ❋
    -0.36
    Šaltiniai
    -0.36
    voyer
    -0.35
     sonra
    -0.35
     Kecamatan
    -0.35
     Bupati
    -0.35
     vigencia
    -0.35
    POSITIVE LOGITS
     isSuccess
    0.71
     merupakan
    0.64
     kind
    0.58
     onderdeel
    0.57
     является
    0.56
    anInt
    0.54
     proud
    0.54
     adalah
    0.54
    是一个
    0.54
     worth
    0.53
    Activations Density 0.231%

    No Known Activations