© 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. 0-GEMMASCOPE-RES-16K
    11. 7437
    Prev
    Next
    INDEX
    Explanations

    references to depth or deep states, often in a physical, emotional, or metaphorical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    MessageTagHelper
    -0.66
    parsedMessage
    -0.59
     '\\;'
    -0.59
    IsMutable
    -0.52
     ModelExpression
    -0.50
     EconPapers
    -0.50
    UrlResolution
    -0.50
    发表于
    -0.49
    hein
    -0.49
    новниш
    -0.48
    POSITIVE LOGITS
     deep
    0.79
     mods
    0.74
     Deep
    0.73
     głę
    0.73
     profonda
    0.71
     глубо
    0.69
    Deep
    0.69
     profond
    0.68
     profound
    0.68
     profundos
    0.67
    Activations Density 0.178%

    No Known Activations