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. 4-GEMMASCOPE-RES-16K
    6. 16002
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tags and elements

    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
    Personendaten
    -1.18
     المعيارى
    -1.14
    ScopeManager
    -1.03
     AssemblyCulture
    -1.03
    IntoConstraints
    -0.99
     Мексичка
    -0.99
    verwijspagina
    -0.98
    ThroughAttribute
    -0.96
     utafitiHapana
    -0.94
     '\\;'
    -0.93
    POSITIVE LOGITS
    ("<
    1.28
    ('<
    1.28
     '<
    1.13
     "<
    1.12
    ="<
    1.09
    "<
    1.03
    '<
    1.00
     $('<
    0.99
     $("<
    0.97
    <!--<
    0.78
    Activations Density 0.177%

    No Known Activations