© 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. 9-GEMMASCOPE-RES-16K
    6. 8050
    Prev
    Next
    INDEX
    Explanations

    the repetition of the word "we," implying a focus on collective experiences or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.80
     Thon
    -0.75
     Paar
    -0.73
     Padang
    -0.69
     Salat
    -0.69
     Monfieur
    -0.68
     Chy
    -0.68
     Ueber
    -0.67
     Rés
    -0.67
    Chy
    -0.67
    POSITIVE LOGITS
    We
    1.55
     We
    1.52
     we
    1.48
    we
    1.33
     WE
    1.14
     I
    1.08
    I
    1.06
     Weinstein
    1.05
     weevil
    1.04
     they
    1.02
    Activations Density 0.189%

    No Known Activations