© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2708
    Prev
    Next
    INDEX
    Explanations

    references to kindness or concepts related to understanding and empathy

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

    "kind" and its context

    np_acts-logits-general · gemini-2.0-flash

    kind of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NavController
    -0.66
     Administrativna
    -0.64
     alertDialog
    -0.63
     McCra
    -0.60
     Salgado
    -0.59
    gasus
    -0.59
    atelli
    -0.59
    AppRoutingModule
    -0.57
    :'/
    -0.56
    CCER
    -0.56
    POSITIVE LOGITS
    kind
    0.68
    Kind
    0.64
    KIND
    0.63
     Kind
    0.60
     kind
    0.60
     KIND
    0.58
     fine
    0.52
    none
    0.52
    ind
    0.52
     Fine
    0.50
    Activations Density 0.144%

    No Known Activations