© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 13040
    Prev
    Next
    INDEX
    Explanations

    terms related to muscle, particularly in a medical or physiological context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -1.10
     NUKAT
    -0.85
    merksamkeit
    -0.76
     ComVisible
    -0.76
    CardModule
    -0.74
     heureuse
    -0.72
    DispatchToProps
    -0.70
    Joanne
    -0.70
    Lorraine
    -0.70
    榈
    -0.68
    POSITIVE LOGITS
    \|_{\
    0.74
    ISATION
    0.71
    y
    0.70
    buss
    0.70
     Fras
    0.68
    :]:
    0.67
    liger
    0.66
    isation
    0.65
    ICAL
    0.64
     createState
    0.63
    Activations Density 0.624%

    No Known Activations