© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 308
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to memory allocation and system configuration

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

    insufficient, improper, or incompatible states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     surla
    -0.56
    RectangleBorder
    -0.48
     خواهیم
    -0.45
     EconPapers
    -0.44
    __(/*!
    -0.43
    richTextPanel
    -0.40
    lepiej
    -0.39
     ferons
    -0.38
    Personensuche
    -0.38
    liseum
    -0.38
    POSITIVE LOGITS
     <>",
    0.67
     or
    0.63
     insufficient
    0.60
     hoặc
    0.60
     terlalu
    0.59
     incorrect
    0.58
     Improper
    0.55
     too
    0.55
     Insufficient
    0.54
     improper
    0.53
    Activations Density 0.076%

    No Known Activations