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

    Neuronpedia

    Jacobian LensNEW
    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. 15-GEMMASCOPE-RES-16K
    11. 491
    Prev
    Next
    INDEX
    Explanations

    actions and processes initiated by the word "By" followed by a gerund or activity

    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
     utafitiHapana
    -0.63
    ftagPool
    -0.54
    nodoc
    -0.52
    GTCX
    -0.51
    EDEFAULT
    -0.51
     Scin
    -0.50
     requestCode
    -0.50
     NSObject
    -0.50
    nash
    -0.50
     OnInit
    -0.49
    POSITIVE LOGITS
     Dadurch
    0.63
     thereby
    0.60
    することで
    0.56
     Damit
    0.54
    Damit
    0.52
     Dzięki
    0.49
    By
    0.49
     thus
    0.46
     By
    0.44
    从而
    0.43
    Activations Density 0.277%

    No Known Activations