© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8306
    Prev
    Next
    INDEX
    Explanations

    perspectives related to various viewpoints or angles on a topic

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

    "... perspective" or "... point of view"

    np_acts-logits-general · gemini-2.0-flash

    from a perspective

    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
     архивлан
    -0.74
    StoryboardSegue
    -0.66
    makeConstraints
    -0.65
    unknownFields
    -0.61
    Obrázky
    -0.60
    Chham
    -0.59
    ConstraintMaker
    -0.58
    SharedDtor
    -0.58
     annonces
    -0.56
    Aholisi
    -0.56
    POSITIVE LOGITS
     perspective
    2.36
    perspective
    1.92
     perspectives
    1.90
     Perspective
    1.87
     viewpoint
    1.82
     perspectiva
    1.81
     PERSPECT
    1.66
    Perspective
    1.64
     view
    1.62
     perspek
    1.59
    Activations Density 0.359%

    No Known Activations