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

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-131K
    11. 102911
    Prev
    Next
    INDEX
    Explanations

    occurrences of the notation associated with storage or memory management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     }}$}
    -0.63
    AndEndTag
    -0.60
     ujednoznacz
    -0.59
    неопр
    -0.56
    /*
    -0.56
    ″]
    -0.55
    '))
    -0.53
    MathML
    -0.51
     Brill
    -0.49
    KommentareTeilen
    -0.49
    POSITIVE LOGITS
    ._
    0.88
    __.__
    0.75
    .__
    0.74
    ]._
    0.71
    ::$_
    0.64
    )._
    0.64
     AssemblyVersion
    0.60
    ().__
    0.58
     ._
    0.56
    ->_
    0.56
    Activations Density 0.023%

    No Known Activations