© 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. 14740
    Prev
    Next
    INDEX
    Explanations

    processes and steps related to manufacturing or mechanical operations

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

    changes or modifications

    np_acts-logits-general · gemini-2.0-flash

    removes, restores, or nullifies

    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
     undergoes
    -0.48
     thrives
    -0.47
     underwent
    -0.47
     monitor
    -0.45
     contributing
    -0.44
     thrived
    -0.44
     advising
    -0.43
     thrive
    -0.43
     undergo
    -0.43
     contribute
    -0.43
    POSITIVE LOGITS
     obliter
    0.60
    把
    0.58
     mengubah
    0.57
     effectively
    0.57
    把她
    0.55
     bring
    0.52
     restores
    0.52
    effectively
    0.52
     nul
    0.52
     removes
    0.52
    Activations Density 1.107%

    No Known Activations