© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 90451
    Prev
    Next
    INDEX
    Explanations

    technical or coding-related elements within the text

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

    fetching database rows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     kasarigan
    -0.51
     فريبيس
    -0.49
     informée
    -0.48
    Vorlage
    -0.42
     AssemblyTitle
    -0.42
     ostensibly
    -0.42
     auguri
    -0.40
     يتيمه
    -0.40
    zbęd
    -0.38
     convite
    -0.38
    POSITIVE LOGITS
    mysqli
    0.59
     mysqli
    0.55
    PHeader
    0.47
     gynhyrchwyd
    0.47
    mysql
    0.44
     mysql
    0.44
    ($_
    0.43
    msgSender
    0.42
    xmlhttp
    0.41
    繫
    0.41
    Activations Density 0.019%

    No Known Activations