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. 1820
    Prev
    Next
    INDEX
    Explanations

    references to mailing addresses and their completeness in the context of applications

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

    Concerns about addresses

    np_acts-logits-general · gemini-2.0-flash

    street and contact addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Vikipedi
    -0.50
    parsedMessage
    -0.49
    protoimpl
    -0.48
    simpleType
    -0.45
    MenuInflater
    -0.45
    Становништво
    -0.43
    Jsp
    -0.43
    DockStyle
    -0.41
    SerializedName
    -0.41
     запу
    -0.41
    POSITIVE LOGITS
     address
    2.84
     Address
    2.49
     addresses
    2.43
    address
    2.42
     ADDRESS
    2.29
    Address
    2.26
     Addresses
    2.15
     adress
    2.11
    ADDRESS
    2.07
    地址
    1.93
    Activations Density 0.230%

    No Known Activations