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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 7036
    Prev
    Next
    INDEX
    Explanations

    references to specific films and their associated actors or production details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.70
     Paredes
    -0.62
    väg
    -0.60
    Busch
    -0.60
     Chiu
    -0.60
     kade
    -0.59
     Saunders
    -0.59
     Busch
    -0.58
     Waite
    -0.57
    ">//
    -0.57
    POSITIVE LOGITS
     Lucca
    0.69
     Damon
    0.69
     Becca
    0.67
     jsPsych
    0.66
    Damon
    0.66
    osovo
    0.65
     CEC
    0.64
     Ariz
    0.63
     lithium
    0.63
     Castro
    0.63
    Activations Density 3.009%

    No Known Activations