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. 9-GEMMASCOPE-RES-16K
    6. 15785
    Prev
    Next
    INDEX
    Explanations

    terms associated with medical treatments for specific diseases, particularly involving monoclonal antibodies and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BibitemShut
    -0.91
    bibinfo
    -0.83
     متعلقه
    -0.74
     clc
    -0.73
     sonora
    -0.72
    styleType
    -0.72
    pegno
    -0.70
    Collegamenti
    -0.69
     Barbier
    -0.69
    bibfield
    -0.69
    POSITIVE LOGITS
    tır
    0.70
    fromCharCode
    0.56
     сент
    0.54
    Puss
    0.51
    арак
    0.51
     محفوظة
    0.51
    CppMethod
    0.51
    t
    0.51
    less
    0.50
     Hov
    0.50
    Activations Density 0.882%

    No Known Activations