Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 2555
    Prev
    Next
    INDEX
    Explanations

    details related to contact information and numerical data

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

    Telephone, fax, or number-related information

    np_acts-logits-general · gemini-2.0-flash

    phone numbers and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.73
    findpost
    -0.71
     مشين
    -0.70
     оригіналу
    -0.70
    #
    -0.66
    MigrationBuilder
    -0.64
    bootstrapcdn
    -0.59
    AccessorTable
    -0.58
    #![
    -0.57
     שוליים
    -0.57
    POSITIVE LOGITS
     
    0.65
    XXXXXX
    0.58
     warszawa
    0.51
    ******
    0.51
     ciudadana
    0.50
     betweenstory
    0.49
     internetowa
    0.49
    xxxxxx
    0.47
     abstracta
    0.46
    JsonFormat
    0.46
    Activations Density 0.145%

    No Known Activations