© 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. 10-GEMMASCOPE-RES-16K
    6. 3273
    Prev
    Next
    INDEX
    Explanations

    references to the name "Joe."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rind
    -0.82
    Портал
    -0.78
     Herv
    -0.77
    Portail
    -0.75
    ので
    -0.75
    )<
    -0.72
     incendi
    -0.72
     nak
    -0.70
    mfenced
    -0.70
    JspWriter
    -0.70
    POSITIVE LOGITS
     Joe
    1.44
    JOE
    1.42
     JOE
    1.33
    Joe
    1.31
     joe
    1.31
     Biden
    1.28
    Biden
    1.27
    joe
    1.18
     Qiao
    1.11
    Joey
    1.02
    Activations Density 0.146%

    No Known Activations