© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 1572
    Prev
    Next
    INDEX
    Explanations

    terms related to horizontal alignment and positioning within layouts or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.67
    RenderAtEndOf
    -0.64
    Hentet
    -0.59
    ipheral
    -0.57
    évaluateur
    -0.57
    parsedMessage
    -0.57
     utafitiHapana
    -0.56
    NameInMap
    -0.56
     defaultstate
    -0.56
     فريبيس
    -0.55
    POSITIVE LOGITS
     reversed
    0.43
     flipped
    0.40
     reversing
    0.39
     flip
    0.38
     inverted
    0.37
     gender
    0.37
     preference
    0.36
     polarity
    0.35
     orientation
    0.34
     opposing
    0.34
    Activations Density 0.820%

    No Known Activations