© 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. 11851
    Prev
    Next
    INDEX
    Explanations

    phrases indicating movement or direction

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

    Directional words: up, down, onto, toward

    np_acts-logits-general · gemini-2.0-flash

    up and toward

    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
    RTLR
    -0.52
     ModelExpression
    -0.43
     fall
    -0.42
     compens
    -0.40
    énario
    -0.37
    easeOut
    -0.36
     progression
    -0.36
     syl
    -0.36
    runOnUiThread
    -0.36
     Grosso
    -0.36
    POSITIVE LOGITS
     autorytatywna
    0.48
    FieldOffsetTable
    0.47
     toward
    0.44
    MutableLiveData
    0.43
    actable
    0.42
    httphttps
    0.40
     onto
    0.40
    tvguidetime
    0.40
     rospy
    0.40
    toward
    0.40
    Activations Density 0.128%

    No Known Activations