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. 1393
    Prev
    Next
    INDEX
    Explanations

    comparisons and conditions involving numerical limits

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

    Less than or equal to operator

    np_acts-logits-general · gemini-2.0-flash

    <= comparison

    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
    ilitation
    -0.64
    se
    -0.64
    rmtree
    -0.64
    ellin
    -0.63
     bit
    -0.62
    ’
    -0.62
     il
    -0.61
    ChromeDriver
    -0.60
    ———
    -0.60
    Herr
    -0.59
    POSITIVE LOGITS
    ]<=
    1.24
     <=
    1.12
     Theſe
    1.07
    <=
    1.05
     cauſe
    1.03
     againſt
    1.01
    )<=
    1.00
     Jefus
    0.99
     uſe
    0.99
     beſt
    0.98
    Activations Density 0.143%

    No Known Activations