© 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. 3-GEMMASCOPE-RES-16K
    11. 6569
    Prev
    Next
    INDEX
    Explanations

    the beginning of various segments or sections within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.48
    ↵↵
    -0.44
     …
    -0.44
     ...
    -0.43
     juuri
    -0.42
     ​
    -0.41
    ↵↵↵
    -0.41
     prominently
    -0.40
    ’
    -0.40
     tremendously
    -0.40
    POSITIVE LOGITS
    featureID
    0.84
    AndEndTag
    0.82
     ſta
    0.75
     surla
    0.71
     AssemblyCulture
    0.66
     ſte
    0.63
    出版年
    0.62
    StructEnd
    0.62
     ſtate
    0.61
     ſy
    0.61
    Activations Density 0.117%

    No Known Activations