© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12740
    Prev
    Next
    INDEX
    Explanations

    terms related to mechanical components and coupling systems

    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
     Theſe
    -1.11
     itſelf
    -1.07
     Anſ
    -1.00
     myſelf
    -0.99
     Houſe
    -0.98
    ITERATURE
    -0.98
     فريبيس
    -0.97
     Monfieur
    -0.97
     Reſ
    -0.95
    enumi
    -0.95
    POSITIVE LOGITS
     suitable
    0.70
     optionally
    0.66
     Ø
    0.65
     Suitable
    0.63
     /
    0.62
    Suitable
    0.58
     
    0.57
    <eos>
    0.56
     standard
    0.55
     possibility
    0.55
    Activations Density 0.493%

    No Known Activations