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. 7069
    Prev
    Next
    INDEX
    Explanations

    terms related to manufacturing processes and material efficiency in production

    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
     methodologies
    -0.55
     wikipagina
    -0.54
    Nv
    -0.53
    RegistryLite
    -0.52
     acum
    -0.52
    ègre
    -0.52
    genöss
    -0.48
    ungsbedingungen
    -0.48
     Breen
    -0.47
    panzer
    -0.47
    POSITIVE LOGITS
    Especially
    0.70
     Incidentally
    0.70
     approx
    0.68
    NUMX
    0.68
    ')")
    0.66
     Hardly
    0.65
    ≙
    0.65
    rungsseite
    0.64
     Particularly
    0.63
     decisivo
    0.62
    Activations Density 0.559%

    No Known Activations