© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105943
    Prev
    Next
    INDEX
    Explanations

    terms related to thresholds and separators in a context, particularly in relation to image processing and boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    dividing or separating things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.45
     Umgang
    -0.44
    +#+#
    -0.41
     TextAppearance
    -0.40
    reportWebVitals
    -0.40
     Mejora
    -0.38
     merve
    -0.38
    choly
    -0.38
    attutto
    -0.37
     tempio
    -0.37
    POSITIVE LOGITS
     dividing
    0.63
     separating
    0.55
     divides
    0.53
     boundary
    0.50
     divider
    0.50
     divide
    0.49
     partition
    0.49
     splitting
    0.48
     split
    0.47
     partitioning
    0.46
    Activations Density 0.216%

    No Known Activations