© 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. 11-GEMMASCOPE-RES-16K
    6. 12854
    Prev
    Next
    INDEX
    Explanations

    technical terms and metrics related to data processing and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tila
    -0.57
    AccessorTable
    -0.54
    zupeł
    -0.51
    љено
    -0.50
    ReusableCell
    -0.48
     Yours
    -0.48
    convertView
    -0.46
    زاد
    -0.46
    CardBody
    -0.46
    Yours
    -0.45
    POSITIVE LOGITS
    ValueStyle
    0.81
     Roskov
    0.73
     isInitialized
    0.70
    endphp
    0.70
     InputDecoration
    0.68
    rungsseite
    0.65
     jadx
    0.63
     initComponents
    0.62
     CreateTagHelper
    0.62
     propOrder
    0.61
    Activations Density 1.100%

    No Known Activations