© 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. 5694
    Prev
    Next
    INDEX
    Explanations

    programming functions and method calls

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

    Code snippets with brackets and symbols

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation in code

    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
     GoogleFonts
    -0.55
    期刊论文
    -0.52
    脚注の使い方
    -0.47
    (©
    -0.47
    Manbalar
    -0.46
    liceerd
    -0.46
    Fis
    -0.46
    zeera
    -0.45
     الحره
    -0.44
     pinulongan
    -0.44
    POSITIVE LOGITS
     financière
    0.46
     financières
    0.44
    principalTable
    0.41
     navideño
    0.40
     ladrillo
    0.38
    twimg
    0.36
     llavero
    0.36
     recevez
    0.36
     bäst
    0.36
     póster
    0.36
    Activations Density 0.174%

    No Known Activations