© 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
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7488
    Prev
    Next
    INDEX
    Explanations

    technical jargon and specific terminology related to processes and methods in various fields

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

    sentence endings and the beginning of new sentences, particularly at the end of paragraphs.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Hundred
    -0.40
    น้อย
    -0.38
     anún
    -0.38
    Dimensões
    -0.37
    égard
    -0.37
     merasa
    -0.37
     erinner
    -0.37
     gewel
    -0.36
     sufrir
    -0.36
    ramientas
    -0.36
    POSITIVE LOGITS
    dafx
    0.56
    principalTable
    0.51
    balleur
    0.48
     snippetHide
    0.47
     noDo
    0.46
     بيها
    0.45
    httphttps
    0.45
    SPATH
    0.45
    astéro
    0.45
    DIPSETTING
    0.44
    Activations Density 1.060%

    No Known Activations