© 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. 28-GEMMASCOPE-RES-16K
    11. 10554
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and calculations related to energy and time

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

    zero, offset, or starting values

    np_acts-logits-general · gemini-2.0-flash

    starting point or zero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.57
    Autoritní
    -0.52
    ScopeManager
    -0.49
    JspWriter
    -0.47
    ImageContext
    -0.46
    GEBURTSDATUM
    -0.41
     فريبيس
    -0.41
     ItemStack
    -0.40
    oredCriteria
    -0.40
     fides
    -0.38
    POSITIVE LOGITS
     zero
    1.03
     offset
    0.98
     starting
    0.90
     Zero
    0.89
    offset
    0.89
     Offset
    0.85
    Zero
    0.85
    zero
    0.84
     zéro
    0.84
     ZERO
    0.84
    Activations Density 0.869%

    No Known Activations