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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5627
    Prev
    Next
    INDEX
    Explanations

    trigonometric functions and their relationships in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     Platon
    -0.42
     Honduras
    -0.38
     aer
    -0.38
    アニ
    -0.37
     Hinsicht
    -0.37
     برس
    -0.36
     biệt
    -0.35
     onely
    -0.35
     Jahrhunderts
    -0.35
    ="../../
    -0.34
    POSITIVE LOGITS
     AssemblyCulture
    0.76
    tanleria
    0.60
    XmlAccessorType
    0.58
    MessageTagHelper
    0.57
     MaterialApp
    0.56
    errHandler
    0.56
    sin
    0.56
    Datuak
    0.55
    Sin
    0.55
     Sin
    0.54
    Activations Density 0.447%

    No Known Activations