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. 23-GEMMASCOPE-RES-16K
    6. 11190
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and functions involving trigonometric terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessorType
    -0.55
     Diallo
    -0.53
     Städ
    -0.53
     Lyd
    -0.51
    createCell
    -0.51
    кипедия
    -0.51
     sula
    -0.51
     zug
    -0.50
    IEDAD
    -0.49
    RegistryLite
    -0.49
    POSITIVE LOGITS
     sin
    2.04
    sin
    1.91
    Sin
    1.74
    cos
    1.71
     cos
    1.71
     Sin
    1.70
    Cos
    1.50
     SIN
    1.46
     Cos
    1.43
     sine
    1.37
    Activations Density 0.634%

    No Known Activations