Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 7792
    Prev
    Next
    INDEX
    Explanations

    references to demographic factors and populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ResumeLayout
    -0.55
     menge
    -0.53
    Tikang
    -0.52
    glDelete
    -0.50
    astéroïdes
    -0.50
    metheus
    -0.48
     tráfico
    -0.48
    kai
    -0.47
     makeStyles
    -0.46
     argc
    -0.46
    POSITIVE LOGITS
     married
    0.83
     employed
    0.74
     working
    0.72
    цезда
    0.68
    married
    0.66
     aged
    0.66
     females
    0.66
     Married
    0.65
     males
    0.64
     female
    0.64
    Activations Density 1.098%

    No Known Activations