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. 3-GEMMASCOPE-RES-16K
    6. 9413
    Prev
    Next
    INDEX
    Explanations

    references to the role or position of a commissioner, particularly in legal or administrative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovács
    -0.72
     Hyman
    -0.66
    verige
    -0.64
     Coyle
    -0.63
    enio
    -0.61
     Hecht
    -0.61
    Linnaeus
    -0.61
    grave
    -0.60
     calldata
    -0.60
    nebago
    -0.59
    POSITIVE LOGITS
     Commissioner
    1.86
     commissioner
    1.84
    Commissioner
    1.59
     commissioners
    1.48
     Commissioners
    1.35
    Miller
    1.29
     Miller
    1.27
     miller
    1.13
     MILLER
    1.07
     '\\;'
    1.05
    Activations Density 0.098%

    No Known Activations