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. 20-GEMMASCOPE-RES-16K
    6. 7431
    Prev
    Next
    INDEX
    Explanations

    phrases that include variations of the word "some."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     intptr
    -0.77
     <<<<<<<<<<<<<<
    -0.71
    UnusedPrivate
    -0.66
     "..\..\..\
    -0.65
    @[+][
    -0.65
     MessageBoxIcon
    -0.64
    ElementException
    -0.63
     protoimpl
    -0.62
    LookAnd
    -0.62
    WireFormat
    -0.60
    POSITIVE LOGITS
     sort
    1.14
    things
    0.95
    sort
    0.91
     kind
    0.91
     degree
    0.81
     Sort
    0.76
     semblance
    0.73
    ones
    0.72
    kind
    0.72
    Sort
    0.71
    Activations Density 0.126%

    No Known Activations