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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8093
    Prev
    Next
    INDEX
    Explanations

    words related to safety and the concept of being safe

    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
    /*!
    -0.46
    exus
    -0.39
    ftant
    -0.38
    wegs
    -0.35
    ┌
    -0.35
    ついて
    -0.34
     '{@
    -0.34
    etar
    -0.34
    sigs
    -0.33
     volu
    -0.33
    POSITIVE LOGITS
     safe
    1.10
     Safe
    1.04
    safe
    0.97
    Safe
    0.96
     SAFE
    0.73
    SAFE
    0.68
    tagHelperRunner
    0.63
     invokingState
    0.62
    AddTagHelper
    0.59
     bezpiecz
    0.59
    Activations Density 0.171%

    No Known Activations