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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 10834
    Prev
    Next
    INDEX
    Explanations

    terms related to retention and restoration in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zzleHttp
    -0.54
    :✨
    -0.52
     дописавши
    -0.52
    tanleria
    -0.50
     تضيفلها
    -0.49
    basicConfig
    -0.48
    migrationBuilder
    -0.46
    Decided
    -0.45
    Simply
    -0.44
     especializada
    -0.43
    POSITIVE LOGITS
     incoming
    1.05
     Incoming
    1.00
     outgoing
    0.98
    Incoming
    0.95
    incoming
    0.93
    outgoing
    0.92
    Outgoing
    0.85
     outbound
    0.60
     inbound
    0.58
     departing
    0.58
    Activations Density 0.111%

    No Known Activations