© 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 - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10068
    Prev
    Next
    INDEX
    Explanations

    the concept of "waking" or awakening, both literally and metaphorically

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.61
    ếng
    -0.60
    Արտաքին
    -0.59
    Portale
    -0.57
    verwijspagina
    -0.57
    Примечания
    -0.57
    AnchorStyles
    -0.56
    ChildScrollView
    -0.56
     Skal
    -0.56
    bitField
    -0.54
    POSITIVE LOGITS
     wake
    0.98
     wakes
    0.76
     waking
    0.74
    wake
    0.72
     awake
    0.66
    libft
    0.65
    loyds
    0.65
    दार
    0.61
     oprot
    0.60
    phors
    0.60
    Activations Density 0.028%

    No Known Activations