© 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. 2-GEMMASCOPE-RES-16K
    11. 15937
    Prev
    Next
    INDEX
    Explanations

    instances of the infinitive verb form "to" followed by various actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setOpen
    -0.38
     souhaitent
    -0.35
    كويكب
    -0.35
     змо
    -0.34
     ugy
    -0.34
     pernyataan
    -0.34
     mulia
    -0.33
     gedaan
    -0.33
     besuchen
    -0.33
    ípio
    -0.33
    POSITIVE LOGITS
     ProtoMessage
    0.64
    aprend
    0.59
    learning
    0.59
     AttributeSet
    0.58
    +#+#
    0.58
     aprend
    0.58
     learning
    0.57
     getItemId
    0.54
    inSlope
    0.54
     Aprend
    0.53
    Activations Density 0.299%

    No Known Activations