© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 1050
    Prev
    Next
    INDEX
    Explanations

    elements that indicate personal experiences or opinions

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

    "...or something like..."

    np_acts-logits-general · gemini-2.0-flash

    something like

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Hvad
    -0.45
    mergeFrom
    -0.44
    เดิม
    -0.41
    JoinTable
    -0.40
    await
    -0.40
    arange
    -0.39
    botten
    -0.39
    Lesen
    -0.39
    foglal
    -0.38
    vels
    -0.38
    POSITIVE LOGITS
     like
    2.52
     Like
    1.79
     LIKE
    1.73
    Like
    1.73
    like
    1.65
    LIKE
    1.42
     seperti
    1.42
     như
    1.32
     semacam
    1.28
     así
    1.26
    Activations Density 0.360%

    No Known Activations