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. 16-GEMMASCOPE-RES-16K
    6. 12390
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and procedural contexts

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

    Opening or closing parentheses

    np_acts-logits-general · gemini-2.0-flash

    ending punctuation after words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VIRONMENT
    -0.50
    GEST
    -0.50
    帖最后由
    -0.49
     NSMutable
    -0.49
    UFACT
    -0.49
    NSObject
    -0.48
     τί
    -0.48
    ☆☆☆☆
    -0.48
    strcmp
    -0.48
    tokio
    -0.47
    POSITIVE LOGITS
    ↵
    1.98
     […]
    1.39
    ↵↵
    1.29
     =
    
    1.21
    ',...
    1.18
    </h3>
    1.17
    ,...
    1.15
     [...]
    1.04
     ..."
    1.04
    </h4>
    1.03
    Activations Density 6.106%

    No Known Activations