© 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. 8066
    Prev
    Next
    INDEX
    Explanations

    words that indicate safety or the lack thereof

    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
     виправивши
    -0.53
    agonia
    -0.46
    IntoConstraints
    -0.45
    الإنجليزية
    -0.45
     HasFactory
    -0.45
    setVerticalGroup
    -0.44
     OFDb
    -0.43
     jeito
    -0.43
     otomatig
    -0.42
    featureID
    -0.42
    POSITIVE LOGITS
     Safe
    0.99
    Safe
    0.97
     safe
    0.96
    safe
    0.91
     safely
    0.81
     Safety
    0.81
     SAFE
    0.80
    Safety
    0.78
    saf
    0.77
    SAFE
    0.77
    Activations Density 0.257%

    No Known Activations