© 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. 14785
    Prev
    Next
    INDEX
    Explanations

    references or citations in academic texts

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

    cited papers ([bib...])

    np_acts-logits-general · gemini-2.0-flash

    small quantities or low values

    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
     higher
    -0.46
    以上
    -0.42
     almeno
    -0.42
    较高
    -0.41
    長い
    -0.41
     Higher
    -0.40
    Longer
    -0.40
     이상
    -0.39
     longer
    -0.38
    以上の
    -0.38
    POSITIVE LOGITS
     barely
    0.98
    わずか
    0.96
     few
    0.81
     wenigen
    0.80
     poucos
    0.79
    不到
    0.77
    たった
    0.77
    few
    0.77
     scant
    0.76
     mere
    0.73
    Activations Density 0.776%

    No Known Activations