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. 11-GEMMASCOPE-RES-16K
    6. 13862
    Prev
    Next
    INDEX
    Explanations

    references to political power struggles and territorial conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     program
    -0.58
     data
    -0.56
     chương
    -0.54
    enschein
    -0.46
    coltà
    -0.46
    program
    -0.46
    zaak
    -0.46
    niak
    -0.46
     Sodom
    -0.45
     context
    -0.45
    POSITIVE LOGITS
    ंदीखरीदारी
    0.85
     useStyles
    0.80
     @"/
    0.79
     defaultstate
    0.72
     negociar
    0.70
     <>",
    0.70
     overthrown
    0.69
     getopt
    0.69
    SBATCH
    0.67
     treaties
    0.67
    Activations Density 0.582%

    No Known Activations