Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11823
    Prev
    Next
    INDEX
    Explanations

    information related to medical treatment and patient care parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ось
    -0.28
    long
    -0.27
     ч
    -0.26
     à
    -0.25
    HasKey
    -0.24
    mtrl
    -0.24
     thôi
    -0.24
     et
    -0.24
     Deinen
    -0.23
     Pol
    -0.22
    POSITIVE LOGITS
    :✨
    0.75
     laſſen
    0.71
     betweenstory
    0.71
    StoryboardSegue
    0.69
    ſehen
    0.69
    ſelf
    0.68
    ſicht
    0.68
    transQ
    0.68
    rbrakk
    0.68
     ویکی‌پدی
    0.66
    Activations Density 0.843%

    No Known Activations