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. 4-GEMMASCOPE-RES-16K
    6. 711
    Prev
    Next
    INDEX
    Explanations

    quantitative comparisons involving values, concentrations, and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.57
    spaceBetween
    -0.55
     her
    -0.50
    ForType
    -0.50
    miyorum
    -0.44
    Jegyzetek
    -0.41
     their
    -0.41
     an
    -0.41
    amment
    -0.41
    SerializedSize
    -0.40
    POSITIVE LOGITS
     AssemblyCompany
    0.89
     تضيفلها
    0.82
     ThemeData
    0.75
     nakalista
    0.70
    ########.
    0.69
    newtheorem
    0.67
    EDEFAULT
    0.66
     Audiodateien
    0.65
     aught
    0.65
     pettico
    0.65
    Activations Density 0.951%

    No Known Activations