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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9870
    Prev
    Next
    INDEX
    Explanations

    instances of reported speech or expressions of opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -1.33
    ]--;
    -1.09
     فريبيس
    -1.05
     nahilalakip
    -1.05
     Wikimedijinoj
    -1.01
    !")
    
    -0.99
    Rhestr
    -0.99
    $.
    
    -0.98
     disambiguazione
    -0.96
    */;
    -0.96
    POSITIVE LOGITS
    :
    1.44
     “
    1.37
    ,“
    1.19
    :“
    1.13
    “
    1.12
     "
    1.11
    ,“
    1.07
    :"
    1.06
    :“
    0.99
     “[
    0.97
    Activations Density 0.282%

    No Known Activations