© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 7332
    Prev
    Next
    INDEX
    Explanations

    references to previous sections and their content organization within the paper

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

    section headers and document organizational markers in academic papers.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EDEFAULT
    -0.44
    обеди
    -0.41
     hug
    -0.39
    DataPropertyName
    -0.39
     Numerade
    -0.38
     StatefulWidget
    -0.37
    講師
    -0.37
     hip
    -0.37
     survivors
    -0.36
    Portale
    -0.35
    POSITIVE LOGITS
     section
    1.93
     Section
    1.76
     sections
    1.69
    Section
    1.68
     Sections
    1.51
     SECTION
    1.46
    section
    1.45
     sección
    1.44
    SECTION
    1.38
     subsection
    1.38
    Activations Density 1.334%

    No Known Activations