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. 3-GEMMASCOPE-RES-16K
    6. 10951
    Prev
    Next
    INDEX
    Explanations

    keywords related to fetching data operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.82
    SequentialGroup
    -0.79
    mongoose
    -0.78
     JNI
    -0.73
    TagMode
    -0.68
    CORBA
    -0.67
    complexContent
    -0.67
    AppCompat
    -0.67
    ToolStrip
    -0.65
    JComboBox
    -0.63
    POSITIVE LOGITS
     fetch
    1.34
     Fetch
    1.30
    fetch
    1.20
    Fetch
    1.20
     FETCH
    1.13
    FETCH
    0.99
     deferred
    0.93
     defer
    0.93
     fetching
    0.90
    fetching
    0.86
    Activations Density 0.042%

    No Known Activations