© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 11386
    Prev
    Next
    INDEX
    Explanations

    patterns of mathematical notation and scientific reporting structures

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

    Comes before or introduces a research section

    np_acts-logits-general · gemini-2.0-flash

    academic paper sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zzleHttp
    -0.76
    IVEREF
    -0.59
    tagHelperRunner
    -0.59
     Numerade
    -0.59
    AccessorTable
    -0.55
    
    -0.54
     المعيارى
    -0.54
     للمعارف
    -0.54
    uxxxx
    -0.53
    IndentedString
    -0.53
    POSITIVE LOGITS
    Abstract
    0.96
     Abstract
    0.88
    ABSTRACT
    0.82
    Purpose
    0.75
     ABSTRACT
    0.74
    BACKGROUND
    0.74
     aims
    0.72
     Aims
    0.70
    目的
    0.69
     Purpose
    0.69
    Activations Density 2.118%

    No Known Activations