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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1028
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical methods and estimators in research papers

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

    following "proposed" or "new" and methods

    np_acts-logits-general · gemini-2.0-flash

    proposed method or approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     Cohn
    -0.34
    ViewFeatures
    -0.33
     Hawking
    -0.32
     Dry
    -0.31
    tinyos
    -0.31
     awful
    -0.31
    shtml
    -0.30
    decin
    -0.29
     famous
    -0.29
     terrible
    -0.29
    POSITIVE LOGITS
    WebElementEntity
    0.61
     approach
    0.57
    approach
    0.54
     OMITTED
    0.53
     متعلقه
    0.52
    Personendaten
    0.52
     scalable
    0.50
    InputTagHelper
    0.48
     kaarangay
    0.48
    dika
    0.47
    Activations Density 1.230%

    No Known Activations