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. 21-GEMMASCOPE-RES-16K
    6. 875
    Prev
    Next
    INDEX
    Explanations

    details related to architecture and construction

    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
     doPost
    -0.49
     kaarangay
    -0.48
    bonucleic
    -0.45
    liothèque
    -0.45
     confronti
    -0.45
     Chí
    -0.44
     Normdatei
    -0.44
    zension
    -0.43
    rangian
    -0.43
     parachute
    -0.42
    POSITIVE LOGITS
     bricks
    1.45
     brick
    1.45
     stone
    1.44
     stones
    1.32
     Bricks
    1.23
     Brick
    1.22
     masonry
    1.20
    brick
    1.17
     Stone
    1.16
     STONE
    1.12
    Activations Density 0.161%

    No Known Activations