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. 506
    Prev
    Next
    INDEX
    Explanations

    terms indicating an increase or improvement in various contexts

    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
     pronta
    -0.54
     équilibr
    -0.52
    巨大的
    -0.52
     kinematics
    -0.51
     répartition
    -0.49
     situazione
    -0.48
     arquitetura
    -0.47
     supérieurs
    -0.47
     procéder
    -0.47
     infinite
    -0.47
    POSITIVE LOGITS
     popularity
    0.91
     complexity
    0.90
     amount
    0.89
     awareness
    0.89
     importance
    0.85
     intensity
    0.84
     aantal
    0.84
     number
    0.84
     involvement
    0.80
     sophistication
    0.80
    Activations Density 0.818%

    No Known Activations