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. 14-GEMMASCOPE-RES-16K
    6. 13061
    Prev
    Next
    INDEX
    Explanations

    keywords and terms related to technology and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.75
    voorbeeld
    -0.70
    endregion
    -0.68
    mender
    -0.65
    moveToFirst
    -0.64
    solr
    -0.61
    ymce
    -0.61
     TextStyle
    -0.61
    a
    -0.61
     Linde
    -0.60
    POSITIVE LOGITS
    pable
    1.18
     Jop
    1.08
     FAP
    1.08
     bop
    1.07
     Wap
    1.05
     Bop
    1.03
    Jep
    1.01
     Mop
    0.99
     cip
    0.97
     Jep
    0.96
    Activations Density 0.922%

    No Known Activations