© 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. 14472
    Prev
    Next
    INDEX
    Explanations

    phrases related to duplicate content and optimization in digital contexts

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

    Follows nouns indicating examples or types

    np_acts-logits-general · gemini-2.0-flash

    inside or within

    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
     actionPerformed
    -0.40
     Outer
    -0.38
    URLException
    -0.38
    PyExc
    -0.37
    chien
    -0.37
    ждународ
    -0.36
    shadowRadius
    -0.36
    bou
    -0.36
    ondes
    -0.35
     VizieR
    -0.35
    POSITIVE LOGITS
     inside
    1.21
     внутри
    1.17
     within
    1.13
     dentro
    0.97
    inside
    0.96
     ingame
    0.96
    within
    0.94
     داخل
    0.93
     WITHIN
    0.93
    Within
    0.90
    Activations Density 1.550%

    No Known Activations