© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8236
    Prev
    Next
    INDEX
    Explanations

    numerical data or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rów
    -0.40
     odpowiedzial
    -0.39
     bekende
    -0.39
     elkaar
    -0.39
     seragam
    -0.38
     sitzen
    -0.37
     turysty
    -0.37
     działal
    -0.36
     czł
    -0.36
     celana
    -0.35
    POSITIVE LOGITS
    脚注の使い方
    0.77
     للاسماء
    0.71
     '\\;'
    0.68
    AndEndTag
    0.67
    protoimpl
    0.67
     betweenstory
    0.65
     Wikimedijinoj
    0.64
    GEBURTSDATUM
    0.64
     AssemblyProduct
    0.64
     ſch
    0.63
    Activations Density 1.683%

    No Known Activations