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. 10-GEMMASCOPE-RES-16K
    6. 15814
    Prev
    Next
    INDEX
    Explanations

    concepts related to justice and its implications

    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
    서는
    -0.54
    igh
    -0.48
    enumerate
    -0.48
     المعيارى
    -0.47
    ']=='
    -0.46
    ICOLON
    -0.46
    UserContext
    -0.46
    enes
    -0.46
    chale
    -0.45
    ghi
    -0.45
    POSITIVE LOGITS
     when
    0.64
    WebVitals
    0.61
    rungsseite
    0.59
    SBATCH
    0.59
    toMatchSnapshot
    0.59
     EconPapers
    0.58
    AccessorTable
    0.57
    StoryboardSegue
    0.57
    WriteLiteral
    0.56
     benefit
    0.56
    Activations Density 0.589%

    No Known Activations