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. 17-GEMMASCOPE-RES-16K
    6. 13335
    Prev
    Next
    INDEX
    Explanations

    confirmations or indications of conditions and needs in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -1.03
    Personendaten
    -0.94
     kasarigan
    -0.91
    InitVars
    -0.86
    出版年
    -0.86
     للاسماء
    -0.84
    OGND
    -0.83
    GEBURTSDATUM
    -0.82
     referenties
    -0.81
     betweenstory
    -0.79
    POSITIVE LOGITS
     stuff
    1.03
     Stuff
    0.87
     STUFF
    0.85
    stuff
    0.79
     legislation
    0.77
    Stuff
    0.77
     information
    0.70
    information
    0.67
    Legislation
    0.65
     gente
    0.65
    Activations Density 0.409%

    No Known Activations