© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 4920
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific regions, contexts, or attributes concerning privacy and social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Exists
    -0.46
    imin
    -0.44
     dihasilkan
    -0.44
     thế
    -0.42
     permitem
    -0.42
    itatea
    -0.41
    Exist
    -0.41
    ờ
    -0.40
    ступление
    -0.40
     Tate
    -0.39
    POSITIVE LOGITS
    rungsseite
    0.95
    DockStyle
    0.91
    Autoritní
    0.90
    GEBURTSDATUM
    0.89
    findpost
    0.87
    RetentionPolicy
    0.85
     للاسماء
    0.84
    IntoConstraints
    0.84
     للمعارف
    0.82
    сылкі
    0.79
    Activations Density 0.038%

    No Known Activations