© 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. 1-GEMMASCOPE-RES-16K
    11. 13997
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms related to medical and biochemical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.78
    انگلیسی
    -0.61
     glandular
    -0.61
     дописавши
    -0.58
     caret
    -0.55
    toes
    -0.53
    فحة
    -0.51
    WillAppear
    -0.51
    <?,
    -0.51
    الحياه
    -0.50
    POSITIVE LOGITS
    dia
    0.69
     Jose
    0.60
     Mak
    0.59
    Jose
    0.56
     demonios
    0.56
    DispatchQueue
    0.53
    testify
    0.53
    nhs
    0.51
    orbit
    0.51
     mak
    0.50
    Activations Density 2.152%

    No Known Activations