© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 15836
    Prev
    Next
    INDEX
    Explanations

    references to academic research documents and their digital object identifiers (DOIs)

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

    http://dx.doi.org/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     Wikimedijinoj
    -0.79
     MainAxisSize
    -0.76
     $_(
    -0.70
    ]")]
    -0.69
    StructEnd
    -0.68
     queſta
    -0.67
    ſelf
    -0.65
    ſelves
    -0.65
     ragaz
    -0.65
    transQ
    -0.64
    POSITIVE LOGITS
    doi
    1.55
     doi
    1.05
    DOI
    0.90
     DOI
    0.83
    Doi
    0.73
     Doi
    0.71
    CrossRef
    0.54
    orcid
    0.40
    arXiv
    0.34
    github
    0.31
    Activations Density 0.004%

    No Known Activations