© 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. 1-GEMMASCOPE-RES-16K
    11. 5542
    Prev
    Next
    INDEX
    Explanations

    references to protective items or concepts related to safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enterOuterAlt
    -0.49
    Diwedd
    -0.47
     typelib
    -0.46
    JspWriter
    -0.44
     gaf
    -0.43
    CppMethod
    -0.42
     glas
    -0.42
    絞
    -0.40
    AnchorTagHelper
    -0.40
    PTS
    -0.39
    POSITIVE LOGITS
     tidur
    0.66
     sonno
    0.65
     lion
    0.63
    DebuggerNonUser
    0.60
     SLEEP
    0.60
     sleeping
    0.59
     sleep
    0.58
     shield
    0.57
    Sleeve
    0.57
     lions
    0.57
    Activations Density 0.280%

    No Known Activations