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. 10-GEMMASCOPE-RES-16K
    6. 15783
    Prev
    Next
    INDEX
    Explanations

    medical studies and research-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.57
    AutoScaleMode
    -0.41
    Dtor
    -0.40
    évaluateur
    -0.40
    Française
    -0.39
    出版年
    -0.39
    روزی
    -0.38
    ➟
    -0.38
    metallic
    -0.38
    typically
    -0.37
    POSITIVE LOGITS
     protoimpl
    0.43
    initComponents
    0.42
    AISSEE
    0.41
    IPAC
    0.41
    rungsseite
    0.40
     ComVisible
    0.40
    Hozzáférés
    0.39
     SEDS
    0.39
     Infórmanos
    0.38
    KommentareTeilen
    0.38
    Activations Density 1.595%

    No Known Activations