© 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. 9-GEMMASCOPE-RES-131K
    11. 54485
    Prev
    Next
    INDEX
    Explanations

    references to different types of JSON and XML reader components in a technical context

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

    Reader

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illoma
    -0.53
    Mel
    -0.46
    ulg
    -0.45
    RTGC
    -0.45
    stagland
    -0.45
     бесс
    -0.44
    Vul
    -0.44
    Burg
    -0.44
    acc
    -0.44
    Klo
    -0.43
    POSITIVE LOGITS
    Reader
    3.17
     Reader
    2.48
     READER
    1.91
    reader
    1.89
     reader
    1.80
     Readers
    1.61
    Readers
    1.55
    Writer
    1.43
    readers
    1.34
    NewReader
    1.24
    Activations Density 0.004%

    No Known Activations