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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 274
    Prev
    Next
    INDEX
    Explanations

    specific terms related to medical and biological classifications, particularly concerning tumors and blood components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.64
     CreateTagHelper
    -0.62
    Tikang
    -0.57
    astify
    -0.52
    PerformLayout
    -0.52
    mobileqq
    -0.52
     חיצוניים
    -0.52
    mybatisplus
    -0.50
     autorytatywna
    -0.50
     favorably
    -0.49
    POSITIVE LOGITS
    webElementXpaths
    0.47
     jsPsych
    0.40
    ONAUT
    0.35
     ää
    0.35
    ])]
    0.35
     "..\..\
    0.33
     altså
    0.33
     kautta
    0.33
    Penulis
    0.31
     iLocal
    0.31
    Activations Density 0.924%

    No Known Activations