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. 5-GEMMASCOPE-RES-16K
    6. 3837
    Prev
    Next
    INDEX
    Explanations

    specific terminology and results related to research aims and objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.83
    Mou
    -0.71
     Busse
    -0.71
    ongiorno
    -0.68
    onaise
    -0.66
     Kalman
    -0.66
     NTS
    -0.66
     Clio
    -0.65
     chez
    -0.65
    volmente
    -0.64
    POSITIVE LOGITS
     specific
    1.96
     Specific
    1.82
     SPECIFIC
    1.78
    specific
    1.70
    Specific
    1.70
    pecific
    1.60
    SPECIFIC
    1.60
     spesifik
    1.44
     specifically
    1.38
     specifics
    1.35
    Activations Density 0.120%

    No Known Activations