© 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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 8731
    Prev
    Next
    INDEX
    Explanations

    references to rounding numbers or the term "round"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.72
    cookieParser
    -0.72
    migrationBuilder
    -0.69
    rrggbb
    -0.68
    XmlAccessorType
    -0.63
     pinulongan
    -0.61
     ModelExpression
    -0.59
     للمعارف
    -0.59
     BrowserModule
    -0.59
    romyalgia
    -0.58
    POSITIVE LOGITS
    trip
    1.02
     robin
    0.89
    robin
    0.84
     ROUND
    0.83
     trip
    0.82
    round
    0.79
     rounds
    0.79
     round
    0.78
    Round
    0.76
    table
    0.75
    Activations Density 0.054%

    No Known Activations