© 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. 10410
    Prev
    Next
    INDEX
    Explanations

    terms related to advancement or sophistication in various contexts

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

    "Advanced" or "advance" as the beginning of a phrase

    np_acts-logits-general · gemini-2.0-flash

    advance to specific terms

    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
     acrylique
    -0.40
    rénées
    -0.39
     webbplats
    -0.38
     Wiktionnaire
    -0.37
     preguntó
    -0.36
     espejos
    -0.36
    lgari
    -0.36
     inmigrantes
    -0.36
    glEnd
    -0.35
    govina
    -0.35
    POSITIVE LOGITS
     Advance
    0.84
     ADVANCE
    0.75
     advance
    0.75
    Advance
    0.74
    advance
    0.68
     Advanced
    0.67
     advanced
    0.65
    vanced
    0.64
     avan
    0.63
     Advances
    0.63
    Activations Density 0.183%

    No Known Activations