© 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. 28-GEMMASCOPE-RES-16K
    11. 11928
    Prev
    Next
    INDEX
    Explanations

    dialogue tags and interactions within conversations

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

    Followed by "I", "aligned", or "certainly"

    np_acts-logits-general · gemini-2.0-flash

    Sequences aligned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     curated
    -0.52
     relatable
    -0.50
     idk
    -0.50
     arguably
    -0.49
     vibe
    -0.49
     incentiv
    -0.49
     nuanced
    -0.48
     tropes
    -0.47
     prioriti
    -0.47
     ️
    -0.47
    POSITIVE LOGITS
     skall
    0.51
    faßt
    0.50
    addCriterion
    0.46
     muß
    0.46
     quelquefois
    0.45
     Người
    0.42
    luß
    0.41
     bedo
    0.41
    Killed
    0.40
    Personendaten
    0.38
    Activations Density 0.398%

    No Known Activations