© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 12662
    Prev
    Next
    INDEX
    Explanations

    sentences that emphasize the words "this" or "that"

    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
     &___
    -0.66
    setVerticalGroup
    -0.65
    RTLD
    -0.64
     صوتيه
    -0.63
     MatDialog
    -0.61
    WithIOException
    -0.61
    RectangleBorder
    -0.60
     Италијани
    -0.59
    ivent
    -0.58
    alyptus
    -0.57
    POSITIVE LOGITS
     was
    0.50
     is
    0.49
     would
    0.46
     wasn
    0.45
     Detta
    0.42
     meant
    0.40
     could
    0.40
    This
    0.40
    Đây
    0.40
     Isso
    0.39
    Activations Density 0.297%

    No Known Activations