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. 14482
    Prev
    Next
    INDEX
    Explanations

    symbolic or procedural elements in the text

    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
    BASEPATH
    -0.85
    Życiorys
    -0.59
    mybatisplus
    -0.55
    abetes
    -0.53
    ậc
    -0.52
    VIRGO
    -0.51
    astify
    -0.50
     eqn
    -0.49
    новниш
    -0.49
    참고
    -0.48
    POSITIVE LOGITS
    </em>
    1.50
    </strong>
    1.47
    </u>
    1.30
    </i>
    1.29
    </b>
    1.27
    </h2>
    1.09
    </code>
    1.01
    </h3>
    0.99
    </sup>
    0.98
    </h6>
    0.98
    Activations Density 0.301%

    No Known Activations