© 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. 24-GEMMASCOPE-RES-16K
    11. 6386
    Prev
    Next
    INDEX
    Explanations

    procedural instructions related to data manipulation and programming

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

    Follow-up steps or actions

    np_acts-logits-general · gemini-2.0-flash

    then or sequencing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ceğine
    -0.46
    MessageWindow
    -0.46
     EconPapers
    -0.44
     screens
    -0.43
    screens
    -0.42
     disambiguazione
    -0.41
    قایناق‌لار
    -0.41
    iterrane
    -0.41
     Bioaccumulative
    -0.40
    usercontent
    -0.40
    POSITIVE LOGITS
     then
    1.28
     Then
    1.07
    Then
    1.03
    then
    0.97
     THEN
    0.93
    然后
    0.84
     سپس
    0.83
     dann
    0.82
     entonces
    0.80
     затем
    0.79
    Activations Density 0.837%

    No Known Activations