© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 1926
    Prev
    Next
    INDEX
    Explanations

    instances and variations of the word "access."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.34
    gente
    -0.32
     CGSize
    -0.32
    yle
    -0.32
     StringVar
    -0.31
     Whitehead
    -0.31
     MaterialApp
    -0.30
     StringUtil
    -0.30
     Dil
    -0.30
    Whi
    -0.30
    POSITIVE LOGITS
     access
    4.47
     Access
    4.31
    access
    4.25
    Access
    4.22
     ACCESS
    3.67
    ACCESS
    3.53
     accesses
    3.28
     acceso
    3.14
     accessing
    3.11
     accès
    3.11
    Activations Density 0.249%

    No Known Activations