© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 11660
    Prev
    Next
    INDEX
    Explanations

    code-related troubleshooting and error messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Diwedd
    -0.55
    APOLIS
    -0.55
     solstice
    -0.53
    setVerticalGroup
    -0.53
    Portale
    -0.53
     perfeito
    -0.53
    äť
    -0.53
    TProtocol
    -0.52
     Euripides
    -0.52
     TimeUnit
    -0.52
    POSITIVE LOGITS
     estekak
    0.83
    protoimpl
    0.67
    InjectMocks
    0.63
    setof
    0.61
     кӀ
    0.60
    WillAppear
    0.60
     gestaltet
    0.59
    WithMany
    0.57
    هن
    0.55
    tellung
    0.55
    Activations Density 0.634%

    No Known Activations