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. 16-GEMMASCOPE-RES-16K
    6. 9119
    Prev
    Next
    INDEX
    Explanations

    references to richness or abundance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "rich" and its variations

    np_acts-logits-general · gemini-2.0-flash

    rich history tapestry culture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.79
    HomeAsUpEnabled
    -0.75
    Према
    -0.72
     heretics
    -0.68
    RegressionTest
    -0.68
    Kanpo
    -0.66
     impractica
    -0.65
     Devlin
    -0.64
    oredCriteria
    -0.63
    DeleteMapping
    -0.63
    POSITIVE LOGITS
     rich
    1.17
     RICH
    1.16
     Rich
    1.09
    Rich
    1.04
    rich
    1.03
    RICH
    0.97
     richer
    0.82
    riched
    0.80
     richness
    0.77
     riche
    0.76
    Activations Density 0.138%

    No Known Activations