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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7853
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to properties and their attributes

    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
     виправивши
    -0.64
     ModelRenderer
    -0.55
    例句
    -0.53
    ächtigen
    -0.50
    gette
    -0.47
    AccessorTable
    -0.47
     متعلقه
    -0.47
     gynhyrchwyd
    -0.46
    جوايز
    -0.45
    )‏
    -0.44
    POSITIVE LOGITS
     true
    1.93
     True
    1.85
    true
    1.81
     TRUE
    1.75
    True
    1.75
     False
    1.71
     false
    1.69
    TRUE
    1.63
    false
    1.58
    False
    1.56
    Activations Density 0.319%

    No Known Activations