© 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. 30-GEMMASCOPE-RES-16K
    11. 15116
    Prev
    Next
    INDEX
    Explanations

    references to specific items and concepts within a narrative context

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

    Follows "this" or "that"

    np_acts-logits-general · gemini-2.0-flash

    this thing

    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
     those
    -0.30
    代
    -0.29
     members
    -0.29
    ợp
    -0.28
    PE
    -0.28
    I
    -0.28
    在上
    -0.27
     dự
    -0.27
     primarily
    -0.27
    τους
    -0.27
    POSITIVE LOGITS
     thing
    0.93
     THING
    0.82
    transQ
    0.81
    mybatisplus
    0.80
     betweenstory
    0.77
    RectangleBorder
    0.74
    NameInMap
    0.73
     amazing
    0.72
    OGND
    0.71
     BorderSide
    0.71
    Activations Density 0.319%

    No Known Activations