© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13175
    Prev
    Next
    INDEX
    Explanations

    terms related to extending or expanding concepts or ideas

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "extend" or forms of it

    np_acts-logits-general · gemini-2.0-flash

    extending or reaching beyond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ագրություններ
    -0.54
    脚注の使い方
    -0.51
    __;
    -0.46
    UserScript
    -0.46
    LookAnd
    -0.44
    GORITH
    -0.42
    astéroïdes
    -0.40
     ControllerBase
    -0.40
    béco
    -0.37
    yticks
    -0.35
    POSITIVE LOGITS
     extend
    1.06
     Extend
    1.01
     extender
    0.91
    Extend
    0.91
     Extending
    0.90
     extends
    0.88
    extended
    0.87
     extending
    0.87
     extended
    0.86
    extend
    0.86
    Activations Density 0.175%

    No Known Activations