Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 7243
    Prev
    Next
    INDEX
    Explanations

    terms related to construction and maintenance activities

    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
    ViewFeatures
    -1.00
    DockStyle
    -0.76
     Мексичка
    -0.72
     '\\;'
    -0.69
     nakalista
    -0.69
    featureID
    -0.68
     AssemblyCulture
    -0.68
     doInBackground
    -0.67
    ✨:
    -0.67
    GEBURTSDATUM
    -0.67
    POSITIVE LOGITS
     existing
    0.91
    Existing
    0.84
     Existing
    0.82
    existing
    0.82
     существу
    0.76
     EXISTING
    0.72
    既存
    0.68
     bestaande
    0.65
    EXIST
    0.65
     old
    0.65
    Activations Density 0.502%

    No Known Activations