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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 7506
    Prev
    Next
    INDEX
    Explanations

    terms related to advanced technology and its applications in science and medicine

    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
    "):
    
    -1.69
    >\<^
    -1.57
    ^(@)
    -1.54
    Amicalement
    -1.53
    '):
    
    -1.52
    %");
    -1.51
    FTFY
    -1.50
    NUMX
    -1.49
    })$}
    -1.49
    \<^
    -1.49
    POSITIVE LOGITS
    The
    1.23
    and
    1.19
    http
    1.13
    is
    1.12
    the
    1.12
    I
    1.11
    with
    1.04
    https
    1.03
    in
    1.02
    to
    1.01
    Activations Density 1.980%

    No Known Activations