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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 1896
    Prev
    Next
    INDEX
    Explanations

    disclaimers and warnings regarding medical and financial advice

    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
    TemporalType
    -0.51
     façons
    -0.50
     CreateTagHelper
    -0.50
    первых
    -0.47
    tamanya
    -0.47
    tedy
    -0.46
    ordnen
    -0.46
    mouseout
    -0.46
    Abit
    -0.45
    őtt
    -0.45
    POSITIVE LOGITS
     disclaimer
    0.86
     Disclaimer
    0.81
     accuracy
    0.75
    Disclaimer
    0.71
     copyright
    0.71
    CLAIMER
    0.70
     assumes
    0.70
     trademarks
    0.69
     opinions
    0.69
     neither
    0.68
    Activations Density 0.464%

    No Known Activations