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. 15-GEMMASCOPE-RES-16K
    6. 1357
    Prev
    Next
    INDEX
    Explanations

    terms related to demographics, economic factors, and environmental influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saddest
    -0.58
    !!!
    -0.57
    !!!!
    -0.56
    :)
    -0.56
     occidentale
    -0.56
    !!
    -0.55
    !!!!!
    -0.53
     bourgeoisie
    -0.52
    ().
    -0.51
     easiest
    -0.51
    POSITIVE LOGITS
    ieteur
    0.71
     snippetHide
    0.70
     betweenstory
    0.69
    .[/
    0.64
    éphane
    0.61
    `,
    
    0.60
     boto
    0.58
    danh
    0.57
    ofday
    0.57
     TextInputType
    0.57
    Activations Density 0.767%

    No Known Activations