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

    Neuronpedia

    APICircuit 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. 25-GEMMASCOPE-RES-16K
    6. 5905
    Prev
    Next
    INDEX
    Explanations

    numerical values and symbols indicating mathematical or computational operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gaff
    -0.84
     Sanders
    -0.75
     Presbyter
    -0.70
     Hines
    -0.70
     Therm
    -0.69
     Garrick
    -0.68
     Zer
    -0.66
     Finn
    -0.66
     Hernando
    -0.65
     Kame
    -0.65
    POSITIVE LOGITS
     Antony
    0.94
     Alison
    0.87
    Antony
    0.83
    Alison
    0.82
     Denison
    0.80
     Hutchison
    0.74
     FSA
    0.72
     Hutchinson
    0.71
     Lal
    0.68
     Kenyon
    0.68
    Activations Density 1.620%

    No Known Activations