© 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. 34-GEMMASCOPE-RES-16K
    11. 3849
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to scientific research and methodology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.57
    StoryboardSegue
    -0.52
    onOptions
    -0.50
     gabbana
    -0.47
    documentElement
    -0.43
    ClientRect
    -0.42
     Normdatei
    -0.42
    دانشنامهٔ
    -0.40
    eterangan
    -0.40
     Exactos
    -0.40
    POSITIVE LOGITS
     needed
    3.44
     necessary
    3.30
    needed
    3.00
     required
    2.95
    necessary
    2.86
     Needed
    2.86
     Necessary
    2.67
    Needed
    2.66
     NEEDED
    2.59
    Necessary
    2.56
    Activations Density 1.487%

    No Known Activations