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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2878
    Prev
    Next
    INDEX
    Explanations

    sequences of code or structured formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens preceding numbers and abbreviations

    np_acts-logits-general · gemini-2.0-flash

    numbers and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ]")]
    -1.38
    FTFY
    -1.37
    ^(@)
    -1.32
    "):
    
    -1.30
    __':
    
    -1.27
    =$?
    -1.27
     مشين
    -1.27
    AllAfrica
    -1.25
    >\<^
    -1.24
    __":
    
    -1.23
    POSITIVE LOGITS
      
    1.10
    and
    1.09
    to
    1.07
    for
    1.07
    has
    1.05
    in
    0.99
    is
    0.99
       
    0.97
    of
    0.96
    de
    0.96
    Activations Density 2.132%

    No Known Activations