Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10810
    Prev
    Next
    INDEX
    Explanations

    words related to safety and protection

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

    "safe" and its related terms

    np_acts-logits-general · gemini-2.0-flash

    safe harbor, safe place, safe zone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    RegressionTest
    -1.02
    AddTagHelper
    -1.00
    complexContent
    -0.84
    ="@+
    -0.79
    ⓧ
    -0.76
    oa̍t
    -0.76
     صوتيه
    -0.73
    gameserver
    -0.73
    ViewImports
    -0.72
     ivelany
    -0.70
    POSITIVE LOGITS
    guarded
    1.11
     Safe
    0.78
     unsafe
    0.78
    SAFE
    0.77
    guards
    0.74
     safer
    0.73
    Saf
    0.72
     safe
    0.71
     safest
    0.71
    saf
    0.70
    Activations Density 0.063%

    No Known Activations