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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 6498
    Prev
    Next
    INDEX
    Explanations

    references to malnutrition and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Upan
    -0.93
    SceneManagement
    -0.86
    SPJ
    -0.84
    timbangkan
    -0.82
     newArr
    -0.81
    #+#
    -0.78
     cérami
    -0.78
     Gracie
    -0.77
    contentLoaded
    -0.76
     fluence
    -0.75
    POSITIVE LOGITS
    Mal
    0.91
     Mal
    0.89
    ical
    0.88
     Malfoy
    0.88
    ous
    0.87
     mal
    0.87
    ない
    0.81
    mal
    0.77
     GTS
    0.77
    НИК
    0.76
    Activations Density 0.717%

    No Known Activations