© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 12917
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associated contexts within scientific and legal documents

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

    Numbers starting with 109

    np_acts-logits-general · gemini-2.0-flash

    numbers and letters in citations

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    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
    ValueStyle
    -0.71
    +#+
    -0.66
    NOPQRST
    -0.64
    ☚
    -0.59
    
    -0.58
    denly
    -0.57
    principalColumn
    -0.57
    AnchorTagHelper
    -0.56
     autorytatywna
    -0.54
    mobileqq
    -0.54
    POSITIVE LOGITS
     Helena
    0.44
     Nevis
    0.44
    ToRefresh
    0.42
    inburgh
    0.41
    Helena
    0.41
     Leit
    0.41
     Elisha
    0.40
    titia
    0.38
    FileNotFound
    0.37
    xil
    0.37
    Activations Density 0.720%

    No Known Activations