© 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. 531
    Prev
    Next
    INDEX
    Explanations

    key terms and concepts related to biomedical research and treatment outcomes

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

    [Word] of [Something]

    np_acts-logits-general · gemini-2.0-flash

    levels and rates

    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
    bauen
    -0.49
     mesmas
    -0.44
     otherwise
    -0.42
     aurez
    -0.42
     poprzed
    -0.41
    .
    -0.41
     Pública
    -0.41
    Ben
    -0.40
    affaires
    -0.40
    ,
    -0.40
    POSITIVE LOGITS
    WriteAttribute
    0.66
     defaultstate
    0.64
     Monfieur
    0.60
    SequentialGroup
    0.59
     myſelf
    0.59
     houſe
    0.57
    }}]{
    0.56
     autorytatywna
    0.56
     fubject
    0.56
     Jefus
    0.54
    Activations Density 1.753%

    No Known Activations