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. 20-GEMMASCOPE-RES-16K
    6. 9247
    Prev
    Next
    INDEX
    Explanations

    technical terms related to semiconductor devices and their components

    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
     kasarigan
    -0.55
    Reprints
    -0.45
    __*/
    -0.44
    실
    -0.44
     Disc
    -0.44
    Източници
    -0.43
    !*\
    -0.43
     ujednoznacz
    -0.43
     насељу
    -0.42
    Disc
    -0.42
    POSITIVE LOGITS
     edges
    1.88
     edge
    1.62
     sides
    1.58
     Edges
    1.50
    edges
    1.50
     borders
    1.43
    sides
    1.40
    edge
    1.29
     border
    1.29
     margins
    1.28
    Activations Density 0.598%

    No Known Activations