© 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. 20-GEMMASCOPE-RES-16K
    11. 5744
    Prev
    Next
    INDEX
    Explanations

    specific numerical data and references to organizations or entities related to various contexts

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

    technical or organizational abbreviations and acronyms (like FAO, UN, SPA, BLM, MS-13, etc.).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -1.03
    tagHelperRunner
    -0.90
     Infórmanos
    -0.87
     transfieras
    -0.82
     Signalez
    -0.81
     AssemblyCulture
    -0.79
    الحياه
    -0.73
    rungsseite
    -0.73
    OGND
    -0.71
    
    -0.69
    POSITIVE LOGITS
     is
    0.56
     was
    0.48
     will
    0.44
     provides
    0.43
     grants
    0.42
    :
    0.41
     vs
    0.40
     are
    0.39
     Author
    0.38
     has
    0.37
    Activations Density 2.013%

    No Known Activations