© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5292
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications and performance analysis

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    lacks specific features

    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
     EconPapers
    -0.50
     kasarigan
    -0.45
    طاق
    -0.42
    РЭ
    -0.41
    TProtocol
    -0.41
    ThroughAttribute
    -0.40
     Numerade
    -0.40
     Jawahar
    -0.38
    ViewFeatures
    -0.37
     LIRE
    -0.37
    POSITIVE LOGITS
     insufficient
    0.66
     lacks
    0.61
     lacked
    0.54
     ineffec
    0.54
     lack
    0.54
     only
    0.54
     terlalu
    0.54
     inadequate
    0.52
     inconsistent
    0.52
     unprepared
    0.50
    Activations Density 1.180%

    No Known Activations