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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 9749
    Prev
    Next
    INDEX
    Explanations

    quantitative data and statistics related to populations and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    下载附件
    -0.59
    Enllaces
    -0.57
     macam
    -0.55
     BeautifulSoup
    -0.54
     &___
    -0.54
     bids
    -0.54
    المكان
    -0.53
    ضاف
    -0.53
    bouts
    -0.53
    сылкі
    -0.53
    POSITIVE LOGITS
    visiae
    0.53
     (>
    0.50
    Portale
    0.49
    ThroughAttribute
    0.48
     QWidget
    0.48
    ächlich
    0.47
     (~
    0.47
    NewUrlParser
    0.46
    WebControls
    0.46
    koning
    0.45
    Activations Density 0.330%

    No Known Activations