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. 13-GEMMASCOPE-RES-16K
    6. 15541
    Prev
    Next
    INDEX
    Explanations

    phrases related to the duration or sustainability of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.67
    +#+#
    -0.64
     AssemblyCulture
    -0.63
    ########.
    -0.61
     defStyleAttr
    -0.56
     Riemann
    -0.54
     manualmente
    -0.54
     ivelany
    -0.54
     kontin
    -0.53
    teenth
    -0.52
    POSITIVE LOGITS
     brief
    0.91
    brief
    0.84
     temporary
    0.83
     Brief
    0.79
     ephemeral
    0.74
     briefly
    0.72
     fleeting
    0.72
     short
    0.72
    Brief
    0.71
     transient
    0.71
    Activations Density 0.485%

    No Known Activations