© 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. 3-GEMMASCOPE-RES-16K
    11. 11752
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific classifications related to biology and medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rüyada
    -0.68
    ிகள்
    -0.59
    рации
    -0.59
    τικός
    -0.56
    ,
    -0.54
    deutschen
    -0.53
     moderna
    -0.53
     SimpleName
    -0.51
    жества
    -0.51
    нциклопедия
    -0.50
    POSITIVE LOGITS
     ujednoznacz
    0.99
    +#+#
    0.93
    NOPQRST
    0.82
    GHIJKLM
    0.82
     للاسماء
    0.81
    gäng
    0.80
    ſem
    0.79
    conhe
    0.77
     aveug
    0.75
    actéristi
    0.75
    Activations Density 1.229%

    No Known Activations