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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8675
    Prev
    Next
    INDEX
    Explanations

    phrases indicating that statements or conclusions may not be absolute or universally applicable

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.62
    DataAnnotations
    -0.60
    ConstraintMaker
    -0.59
     groupBox
    -0.50
     محفوظة
    -0.48
     HasFactory
    -0.48
     MainAxisSize
    -0.47
    enteuer
    -0.46
    addGap
    -0.45
    expandindo
    -0.45
    POSITIVE LOGITS
    不一定
    0.66
    未必
    0.60
     necessarily
    0.55
     nemus
    0.54
    alleros
    0.44
    necessarily
    0.43
    windowFixed
    0.43
    Personendaten
    0.41
     noDo
    0.40
    хьтан
    0.40
    Activations Density 0.356%

    No Known Activations