© 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. 28-GEMMASCOPE-RES-16K
    11. 4377
    Prev
    Next
    INDEX
    Explanations

    specific numerical values and phrases related to statistics or game outcomes

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

    winning or losing

    np_acts-logits-general · gemini-2.0-flash

    game outcomes and contest results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    étoit
    -0.48
    \{\\
    -0.44
    iibo
    -0.41
    featureID
    -0.41
     Meksiku
    -0.40
    énario
    -0.37
    ากาศ
    -0.36
     Darts
    -0.36
    anuts
    -0.36
    lorette
    -0.36
    POSITIVE LOGITS
     victory
    1.16
     win
    1.13
     wins
    1.05
     victories
    1.05
     defeat
    0.92
     defeats
    0.84
     victorious
    0.84
     vitória
    0.80
     winning
    0.80
    victory
    0.80
    Activations Density 0.136%

    No Known Activations