© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 3014
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly those associated with significant roles or events

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

    Appears before or after a name

    np_acts-logits-general · gemini-2.0-flash

    Recognized first names followed by second name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intptr
    -0.70
    OGND
    -0.54
     Мексичка
    -0.53
     فريبيس
    -0.52
    Vidite
    -0.44
    Personensuche
    -0.42
     bodyParser
    -0.40
     Mérimée
    -0.39
    ViewFeatures
    -0.39
    epresidente
    -0.38
    POSITIVE LOGITS
     للمعارف
    0.46
     võimal
    0.41
     vooraf
    0.41
     meisjes
    0.40
     læng
    0.40
     aprobado
    0.39
     nødven
    0.39
     tæn
    0.39
     burbujas
    0.38
    tranno
    0.38
    Activations Density 0.157%

    No Known Activations