© 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. 2024
    Prev
    Next
    INDEX
    Explanations

    terms related to commonality or shared attributes among different entities

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

    "common"

    np_acts-logits-general · gemini-2.0-flash

    common followed by a noun

    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
     المعيارى
    -0.49
    łbym
    -0.49
    Rüyada
    -0.47
    printStackTrace
    -0.43
    XmlAccessorType
    -0.43
    ウンサー
    -0.42
     CGRectMake
    -0.41
    ResumeLayout
    -0.40
    phrine
    -0.39
    routeProvider
    -0.38
    POSITIVE LOGITS
     common
    1.05
     Common
    1.02
    Common
    0.98
    common
    0.96
     shared
    0.90
     COMMON
    0.89
     Shared
    0.88
    COMMON
    0.83
     wspól
    0.77
    shared
    0.77
    Activations Density 0.195%

    No Known Activations