© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 90057
    Prev
    Next
    INDEX
    Explanations

    data structure terminology and types related to programming

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

    C++ standard library containers and pointers

    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
     Administrativna
    -0.59
    avadoc
    -0.56
     EconPapers
    -0.49
    EndContext
    -0.49
    出版年
    -0.46
     Lordship
    -0.45
    |()
    -0.44
     embaj
    -0.43
    didSet
    -0.43
    DotNetBar
    -0.43
    POSITIVE LOGITS
    WBC
    0.37
    principalColumn
    0.34
     Photocase
    0.34
     type
    0.34
    Microkernel
    0.34
    nezeu
    0.33
    BeginInit
    0.33
    huawei
    0.33
     edge
    0.33
    picas
    0.33
    Activations Density 0.009%

    No Known Activations