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. 505
    Prev
    Next
    INDEX
    Explanations

    emphasized qualities and characteristics related to experiences or concepts

    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
     betweenstory
    -1.25
    GEBURTSDATUM
    -1.12
    enderror
    -0.96
    expandindo
    -0.93
    Демографія
    -0.93
    RegressionTest
    -0.91
    LookAnd
    -0.90
     AssemblyCompany
    -0.90
     calendriers
    -0.89
    حوالہ
    -0.89
    POSITIVE LOGITS
     enough
    0.92
     to
    0.87
     for
    0.78
     in
    0.67
     as
    0.61
     only
    0.56
     with
    0.56
     from
    0.56
     about
    0.56
     both
    0.55
    Activations Density 0.535%

    No Known Activations