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. 21-GEMMASCOPE-RES-16K
    6. 1031
    Prev
    Next
    INDEX
    Explanations

    information related to educational backgrounds and professional experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    <eos>
    -1.04
    ↵↵
    -0.75
    Chham
    -0.65
     wikipagina
    -0.65
    Portály
    -0.65
     Wikiseite
    -0.60
    expandindo
    -0.59
     Roskov
    -0.59
     JADX
    -0.57
    liferay
    -0.56
    POSITIVE LOGITS
    </strong>
    3.38
    </u>
    2.94
    </em>
    2.84
    </b>
    2.80
    </h2>
    2.59
    </h4>
    2.38
    </i>
    2.26
    </h3>
    2.25
    </h5>
    2.18
    </code>
    2.15
    Activations Density 2.212%

    No Known Activations