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. 11-GEMMASCOPE-RES-16K
    6. 5508
    Prev
    Next
    INDEX
    Explanations

    verbs related to the act of using something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.98
     BorderRadius
    -0.98
    ConstraintMaker
    -0.93
     AppComponent
    -0.88
     MessageBoxIcon
    -0.88
     Aspire
    -0.86
     akka
    -0.86
    :✨
    -0.85
     chakras
    -0.84
     PSM
    -0.84
    POSITIVE LOGITS
     use
    1.27
     Use
    1.15
     USE
    1.13
     uses
    1.10
    setUse
    1.10
     used
    1.08
    Use
    1.08
    USE
    1.05
    ToUse
    1.02
    use
    1.01
    Activations Density 0.256%

    No Known Activations