Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 498
    Prev
    Next
    INDEX
    Explanations

    references to event venues and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.81
    AsUp
    -0.62
    findpost
    -0.59
     doulou
    -0.57
    RenderAtEndOf
    -0.56
     khoe
    -0.55
     BorderSide
    -0.54
    WriteTagHelper
    -0.54
    tvguidetime
    -0.52
    ricist
    -0.51
    POSITIVE LOGITS
     conference
    1.64
     Meeting
    1.44
     meeting
    1.42
    Conference
    1.41
     Conference
    1.41
    Meeting
    1.36
     conferences
    1.34
    conference
    1.30
     CONFERENCE
    1.29
    meeting
    1.26
    Activations Density 0.127%

    No Known Activations