© 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
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 3118
    Prev
    Next
    INDEX
    Explanations

    information related to sports wins and records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pyx
    -0.35
    MeasureSpec
    -0.34
    exitRule
    -0.33
    InSection
    -0.33
    InputTagHelper
    -0.31
     MotionEvent
    -0.28
     forState
    -0.27
     SQLAlchemy
    -0.27
    Hound
    -0.27
     technologies
    -0.26
    POSITIVE LOGITS
     utafitiHapana
    0.66
     ddelweddau
    0.60
     NSCoder
    0.59
     faſt
    0.59
     undefeated
    0.58
     raiſ
    0.57
    fjspx
    0.56
    URLException
    0.56
     purpoſe
    0.55
     chi̍t
    0.54
    Activations Density 0.112%

    No Known Activations