© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5743
    Prev
    Next
    INDEX
    Explanations

    direct quotes and speech patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Xan
    -0.38
    MethodInfo
    -0.35
    äld
    -0.34
    Xan
    -0.34
    ILog
    -0.34
    CURLOPT
    -0.34
    ION
    -0.34
    prus
    -0.33
    genstein
    -0.33
     discur
    -0.33
    POSITIVE LOGITS
    MessageOf
    0.71
     CreateTagHelper
    0.59
    matchCondition
    0.54
    ViewFeatures
    0.52
     Komunikasi
    0.51
    UnusedPrivate
    0.50
    expandindo
    0.50
    AccessorTable
    0.48
    ContentAsync
    0.47
    CodedInputStream
    0.47
    Activations Density 0.127%

    No Known Activations