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. 10191
    Prev
    Next
    INDEX
    Explanations

    structured programming language code and instructions

    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
    <h2>
    -1.46
    </h2>
    -1.45
    <h3>
    -1.36
    </h3>
    -1.28
    <h4>
    -1.24
    .</
    -1.16
    </h1>
    -1.13
    ")){
    
    -1.09
    </h5>
    -1.08
    </h4>
    -1.05
    POSITIVE LOGITS
     houſe
    1.20
     Houſe
    1.18
     myſelf
    1.18
     Monfieur
    1.14
     ſche
    1.14
     Majefty
    1.13
     purpoſe
    1.12
     beſt
    1.11
     Shakspeare
    1.09
     Theſe
    1.09
    Activations Density 0.030%

    No Known Activations