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. 24-GEMMASCOPE-RES-16K
    6. 4192
    Prev
    Next
    INDEX
    Explanations

    terms related to financial performance and management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by "of", "to", "well", or "."

    np_acts-logits-general · gemini-2.0-flash

    list of or history of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused61>
    -0.88
    <unused63>
    -0.86
    <unused62>
    -0.83
    <unused60>
    -0.77
    .
    -0.70
    ↵
    -0.67
    ↵↵
    -0.66
     
    -0.54
      
    -0.54
    ,
    -0.52
    POSITIVE LOGITS
     myſelf
    1.99
     Monfieur
    1.93
     Theſe
    1.84
     ſeveral
    1.79
     itſelf
    1.76
     Efq
    1.76
     whoſe
    1.74
     Jefus
    1.72
     pleaſure
    1.71
     purpoſe
    1.69
    Activations Density 1.072%

    No Known Activations