© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11467
    Prev
    Next
    INDEX
    Explanations

    articles and quantifiers in phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.87
    IUrlHelper
    -0.84
    нгред
    -0.72
     nahilalakip
    -0.71
    Tembelea
    -0.71
    TintMode
    -0.69
     queſta
    -0.67
    GOTREF
    -0.67
    RenderAtEndOf
    -0.66
     queſto
    -0.65
    POSITIVE LOGITS
     someone
    0.45
    guien
    0.42
     A
    0.42
     An
    0.40
    A
    0.40
    Someone
    0.39
    An
    0.38
     seseorang
    0.38
     a
    0.38
    Any
    0.36
    Activations Density 0.568%

    No Known Activations