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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 6093
    Prev
    Next
    INDEX
    Explanations

    legal concepts related to personal rights and protections

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

    "protect" and "protection"

    np_acts-logits-general · gemini-2.0-flash

    protection and defense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.57
     GeoNames
    -0.54
    évaluateur
    -0.54
    mények
    -0.52
     урна
    -0.49
    UrlResolution
    -0.47
    ArgsConstructor
    -0.43
    quelize
    -0.42
    upsi
    -0.42
     impatient
    -0.41
    POSITIVE LOGITS
     protection
    3.49
     protect
    3.07
     protecting
    3.05
     Protection
    3.04
    protection
    3.00
    Protection
    2.91
     protects
    2.84
     Protect
    2.77
     PROTECTION
    2.75
     protective
    2.75
    Activations Density 0.724%

    No Known Activations