© 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. 10130
    Prev
    Next
    INDEX
    Explanations

    information about academic programs and their accreditation

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

    Academic programs and degrees

    np_acts-logits-general · gemini-2.0-flash

    academic programs and degrees

    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
     school
    -0.95
    School
    -0.82
    school
    -0.81
     schools
    -0.81
     School
    -0.80
     Schools
    -0.80
    schools
    -0.76
    Schools
    -0.76
     SCHOOL
    -0.76
     école
    -0.73
    POSITIVE LOGITS
    tagHelperRunner
    0.64
    Personensuche
    0.57
    ArrowToggle
    0.56
    InjectAttribute
    0.55
    RegistryLite
    0.52
    IVEREF
    0.51
     חיצוניים
    0.49
    astéroïdes
    0.49
    OGND
    0.49
     مرئيه
    0.48
    Activations Density 0.143%

    No Known Activations