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. 12-GEMMASCOPE-RES-16K
    6. 12365
    Prev
    Next
    INDEX
    Explanations

    HTML or markup language elements, particularly related to formatting and display attributes

    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
    },[
    -0.90
    ="/">
    -0.89
    ([{
    -0.89
     ['./
    -0.83
    ']));
    -0.80
     /\.(
    -0.77
    ].[
    -0.77
    ()?;
    -0.76
     artesanales
    -0.74
    /*
    -0.73
    POSITIVE LOGITS
    quot
    1.04
     resourceCulture
    1.04
    rdquo
    0.88
     quot
    0.83
    HomeAsUpEnabled
    0.80
    nbsp
    0.75
    VIAF
    0.75
    
    0.72
    cshtml
    0.72
    XmlRootElement
    0.72
    Activations Density 0.063%

    No Known Activations