© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 6762
    Prev
    Next
    INDEX
    Explanations

    instances of the word "entirely" and its variations, indicating a focus on completeness or wholeness in the text context

    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
     McManus
    -0.76
     المعيارى
    -0.73
    UGHS
    -0.71
    Rujukan
    -0.71
     really
    -0.68
    앵
    -0.67
    ParallelGroup
    -0.67
    ilets
    -0.67
     oops
    -0.66
    tigungs
    -0.66
    POSITIVE LOGITS
     accordingly
    1.01
     Normdatei
    0.89
     respectivas
    0.82
     respective
    0.81
     respectivos
    0.81
     thereon
    0.78
     asimismo
    0.72
    Accordingly
    0.70
     Accordingly
    0.68
     ello
    0.68
    Activations Density 0.077%

    No Known Activations