© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12175
    Prev
    Next
    INDEX
    Explanations

    phrases indicating knowledge or statements of fact

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

    To the best of our knowledge

    np_acts-logits-general · gemini-2.0-flash

    this is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    til
    -0.35
     quoque
    -0.35
    GTCX
    -0.32
    sune
    -0.30
    反而
    -0.30
    竟然
    -0.30
    jsii
    -0.29
    lab
    -0.28
     til
    -0.28
     certain
    -0.28
    POSITIVE LOGITS
    這是
    1.43
    这是
    1.42
     đây
    1.34
     это
    1.23
    这是一
    1.20
    これは
    1.20
    这就是
    1.18
     Đây
    1.16
    這就是
    1.16
    これが
    1.14
    Activations Density 0.368%

    No Known Activations