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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 2860
    Prev
    Next
    INDEX
    Explanations

    phrases consisting of the word "a" or variations of "of a"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     very
    -0.55
     more
    -0.54
    -
    -0.50
     full
    -0.48
     
    -0.47
     //
    -0.46
     -
    -0.46
     has
    -0.46
     so
    -0.45
     or
    -0.45
    POSITIVE LOGITS
     Efq
    1.23
    UnknownFieldSet
    1.19
     myſelf
    1.19
    GEBURTSDATUM
    1.18
     Monfieur
    1.16
    ItemBackground
    1.15
    saraba
    1.11
     Jefus
    1.09
    oredCriteria
    1.08
     disponibilités
    1.06
    Activations Density 0.124%

    No Known Activations