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. 9782
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to mechanical systems and engineering

    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
     שוליים
    -0.96
    IntoConstraints
    -0.88
     ProtoMessage
    -0.87
    enderror
    -0.80
    RetentionPolicy
    -0.80
     Normdatei
    -0.78
     NSCoder
    -0.78
    ftagPool
    -0.76
    rawDesc
    -0.75
    stateProvider
    -0.74
    POSITIVE LOGITS
     mechanisms
    0.52
    nical
    0.51
    ので
    0.50
    mechan
    0.49
     mekan
    0.48
    Mechanisms
    0.48
     laun
    0.47
    nis
    0.46
     Mechanisms
    0.45
     Teil
    0.45
    Activations Density 0.114%

    No Known Activations