© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 3878
    Prev
    Next
    INDEX
    Explanations

    references to rules or guidelines for account verification and privacy policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.88
     OMITBAD
    -0.86
     queſto
    -0.84
     zwiſchen
    -0.84
    ロウィン
    -0.84
    
    -0.84
    <unused68>
    -0.83
    PreferredItem
    -0.82
    <unused8>
    -0.82
    <unused14>
    -0.82
    POSITIVE LOGITS
    这
    0.47
    これ
    0.46
     is
    0.46
    Isso
    0.42
     isso
    0.42
     Это
    0.41
    This
    0.40
     这
    0.39
    這
    0.39
     это
    0.38
    Activations Density 0.182%

    No Known Activations