© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4484
    Prev
    Next
    INDEX
    Explanations

    phrases indicating measurement variations and their implications in research contexts

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

    preceding adjectives

    np_acts-logits-general · gemini-2.0-flash

    qualities and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IndentedString
    -0.78
    <?
    -0.69
    PasswordField
    -0.63
    Pautan
    -0.57
    `;
    -0.55
    )‏
    -0.55
    ้อน
    -0.53
    ]){
    -0.51
    "){
    -0.50
    '){
    -0.50
    POSITIVE LOGITS
    toHave
    0.55
     HasFactory
    0.52
     볼
    0.51
     chré
    0.51
    得多
    0.49
    écri
    0.48
    niche
    0.48
    Ệ
    0.48
     éte
    0.48
    Auswahl
    0.47
    Activations Density 0.090%

    No Known Activations