© 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27879
    Prev
    Next
    INDEX
    Explanations

    expressions related to richness and depth

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

    rich

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    RegressionTest
    -0.94
     <=",
    -0.91
     betweenstory
    -0.89
    ConstraintMaker
    -0.88
    oredCriteria
    -0.84
    Према
    -0.82
    DeleteMapping
    -0.80
     reformation
    -0.79
     heretics
    -0.78
    HomeAsUpEnabled
    -0.77
    POSITIVE LOGITS
     rich
    1.13
     Rich
    1.09
     RICH
    1.07
    rich
    1.03
    Rich
    1.00
    RICH
    0.93
    riched
    0.83
     richer
    0.79
     richness
    0.77
     riche
    0.75
    Activations Density 0.046%

    No Known Activations