© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8206
    Prev
    Next
    INDEX
    Explanations

    non-verbal cues or indications of emotional states

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

    numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers, currency, and multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TargetException
    -0.45
     وتسجيلات
    -0.44
     Archiproducts
    -0.39
     Conse
    -0.39
     ചെയ
    -0.38
    ihnach
    -0.37
    Rujuakan
    -0.37
     ise
    -0.37
     реа
    -0.36
     оригіналу
    -0.36
    POSITIVE LOGITS
    <bos>
    0.73
     engraçadas
    0.66
     digitais
    0.56
     zijne
    0.56
     militaires
    0.54
     ſmall
    0.53
     financeira
    0.49
     głó
    0.49
     femininas
    0.49
     $_(
    0.48
    Activations Density 1.920%

    No Known Activations