© 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. 10-GEMMASCOPE-RES-16K
    6. 4166
    Prev
    Next
    INDEX
    Explanations

    instructions and requests related to registrations and appointments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.78
    曖昧さ回避
    -0.71
    IndentedString
    -0.69
    InteropServices
    -0.68
    EDEFAULT
    -0.68
    OGND
    -0.65
    featureID
    -0.65
    verwijspagina
    -0.63
     uintptr
    -0.62
     betweenstory
    -0.61
    POSITIVE LOGITS
     online
    0.57
    persky
    0.55
    Widgets
    0.52
    foglal
    0.51
     clicking
    0.49
    synaptic
    0.49
    CLICK
    0.49
    syste
    0.48
     downloadable
    0.48
     tamu
    0.48
    Activations Density 0.159%

    No Known Activations