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. 16-GEMMASCOPE-RES-16K
    6. 9138
    Prev
    Next
    INDEX
    Explanations

    references to biological mechanisms and responses

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

    Refers to studies done on mice

    np_acts-logits-general · gemini-2.0-flash

    animal studies or models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.65
     móvel
    -0.60
    tionary
    -0.59
     Doctors
    -0.58
    ionView
    -0.56
    Doctors
    -0.56
     retraite
    -0.55
     doctors
    -0.54
    guenos
    -0.53
     collectif
    -0.53
    POSITIVE LOGITS
     mice
    1.02
     mouse
    0.86
     murine
    0.85
     Mice
    0.82
    mice
    0.80
     rats
    0.76
     Mouse
    0.71
    mouse
    0.69
    Mice
    0.68
     Rats
    0.66
    Activations Density 2.483%

    No Known Activations