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. 25-GEMMASCOPE-RES-16K
    6. 4427
    Prev
    Next
    INDEX
    Explanations

    information regarding food items being served, prepared, or presented in specific contexts

    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
    UserScript
    -0.61
     يتيمه
    -0.60
    INSTANCE
    -0.57
     extré
    -0.56
     '\\;'
    -0.54
     lisesi
    -0.52
    ucket
    -0.50
    criture
    -0.50
    celes
    -0.49
     evacuation
    -0.48
    POSITIVE LOGITS
     raw
    0.81
     naked
    0.79
     uncut
    0.78
     unplugged
    0.72
     unfinished
    0.69
     unbound
    0.69
     unfolded
    0.69
     bare
    0.68
     unwra
    0.67
     plain
    0.67
    Activations Density 0.375%

    No Known Activations