© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13989
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to safety and security

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

    "safe" or "safety"

    np_acts-logits-general · gemini-2.0-flash

    safe and effective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yarnpkg
    -0.49
     mídia
    -0.46
    Tikang
    -0.43
     Opus
    -0.43
    lungen
    -0.43
     typewriter
    -0.43
     subscribers
    -0.42
    Itr
    -0.42
    llus
    -0.42
     mustache
    -0.41
    POSITIVE LOGITS
    Safe
    1.21
    Safety
    1.16
     Safe
    1.15
    safe
    1.09
    safety
    1.09
     Safety
    1.08
     SAFETY
    1.08
    SAFE
    1.05
     SAFE
    1.05
     safety
    1.04
    Activations Density 0.068%

    No Known Activations