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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 11031
    Prev
    Next
    INDEX
    Explanations

    instances of quantity and frequency

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

    Follows numbers indicating frequency

    np_acts-logits-general · gemini-2.0-flash

    counting times

    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
    Jährige
    -0.36
    IntoConstraints
    -0.34
    CppCodeGen
    -0.34
    Filmografie
    -0.30
    isfile
    -0.30
     Nacionales
    -0.30
     MonoBehaviour
    -0.29
    endregion
    -0.29
     podrá
    -0.29
    SaveChangesAsync
    -0.28
    POSITIVE LOGITS
     times
    1.51
     veces
    1.14
     fois
    1.11
     TIMES
    1.08
    times
    1.05
     vezes
    1.01
     gånger
    0.96
     Times
    0.93
    TIMES
    0.91
    Times
    0.90
    Activations Density 0.230%

    No Known Activations