Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 13977
    Prev
    Next
    INDEX
    Explanations

    words related to the medical field, particularly those associated with lung conditions and surgical interventions

    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
    Rohy
    -0.59
     blank
    -0.55
     mostrarán
    -0.53
     opérateur
    -0.51
    Enllaces
    -0.51
    conceito
    -0.48
     وتسجيلات
    -0.48
    cheibe
    -0.47
    *)(
    -0.47
     الأق
    -0.47
    POSITIVE LOGITS
    脚注の使い方
    1.01
    enumi
    1.00
     חיצוניים
    0.86
    CloseOperation
    0.69
    basicConfig
    0.66
     wealth
    0.65
    Portale
    0.64
    BufferException
    0.63
    wealth
    0.61
    Accreditation
    0.61
    Activations Density 2.269%

    No Known Activations