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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7324
    Prev
    Next
    INDEX
    Explanations

    geometric and mathematical concepts related to coordinates and plotting points

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

    coordinates or locations

    np_acts-logits-general · gemini-2.0-flash

    plotting points individually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entait
    -0.32
    lapsingToolbar
    -0.28
    kamers
    -0.28
     Dowling
    -0.28
     Alfaro
    -0.28
    albero
    -0.27
    SetString
    -0.27
     niveles
    -0.27
     komment
    -0.27
     pergunt
    -0.26
    POSITIVE LOGITS
    TypedDataSet
    0.79
     MotionEvent
    0.77
    EndGlobalSection
    0.76
    ReusableCell
    0.73
     points
    0.70
    Datuak
    0.67
     POINTS
    0.66
     Points
    0.65
    AndEndTag
    0.65
    points
    0.64
    Activations Density 1.357%

    No Known Activations