© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 152
    Prev
    Next
    INDEX
    Explanations

    elements related to data management and database operations

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

    Code or data snippets

    np_acts-logits-general · gemini-2.0-flash

    `set` or `B` followed by block delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     
    -0.76
    "
    -0.73
    )
    -0.71
    >
    -0.68
    ...
    -0.67
    :
    -0.65
    -
    -0.65
     "
    -0.64
    !
    -0.64
    </strong>
    -0.63
    POSITIVE LOGITS
     للمعارف
    1.19
     pleaſure
    1.11
     raiſ
    1.07
     ſeveral
    1.05
     Monfieur
    1.02
     poffible
    1.01
     ſever
    1.01
    ItemBackground
    1.00
     purpoſe
    0.99
     myſelf
    0.99
    Activations Density 1.863%

    No Known Activations