© 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 EvalsExportsAPI 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. 5413
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and time durations in relation to various subjects

    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
    osoba
    -0.62
    woon
    -0.51
     ASAP
    -0.47
    ace
    -0.47
     statt
    -0.46
     segera
    -0.46
     forthwith
    -0.45
     asap
    -0.45
    esco
    -0.45
    PhysRevD
    -0.44
    POSITIVE LOGITS
     zuletzt
    1.29
     recently
    1.21
    recently
    1.15
     Lately
    1.15
     Recently
    1.15
    每一次
    1.13
     always
    1.13
     derni
    1.11
     lately
    1.09
    Recently
    1.09
    Activations Density 0.302%

    No Known Activations