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. 20-GEMMASCOPE-RES-16K
    6. 653
    Prev
    Next
    INDEX
    Explanations

    actions and verbs related to creating or producing outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.96
    Personendaten
    -0.82
     ProtoMessage
    -0.76
    Tembelea
    -0.72
    vician
    -0.71
     MainAxisSize
    -0.69
    IUrlHelper
    -0.69
    AsUp
    -0.68
     AssemblyVersion
    -0.68
     يتيمه
    -0.67
    POSITIVE LOGITS
     sure
    1.19
     adjustments
    0.84
     arrangements
    0.81
     efforts
    0.74
     plans
    0.71
     changes
    0.71
     use
    0.70
     a
    0.69
    Arrangements
    0.69
    sure
    0.67
    Activations Density 0.095%

    No Known Activations