© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 3863
    Prev
    Next
    INDEX
    Explanations

    coding elements related to event handling and references in programming

    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
    idom
    -0.53
     Kombat
    -0.51
    inerja
    -0.47
    ValueGenerated
    -0.46
     kotlinx
    -0.46
     McCon
    -0.46
    igshid
    -0.45
     vocational
    -0.45
     appren
    -0.44
    աք
    -0.44
    POSITIVE LOGITS
     препратки
    0.81
     שוליים
    0.73
    awtextra
    0.68
     referenties
    0.66
    ſt
    0.65
    RunWith
    0.64
     صوتيه
    0.63
    DoubleQuotes
    0.61
     endwhile
    0.60
    getMenuInflater
    0.60
    Activations Density 0.022%

    No Known Activations