© 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-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 9103
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight defensive justifications or rationalizations for actions taken in controversial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.44
     TestBed
    -0.41
     resourceCulture
    -0.41
    istoitu
    -0.38
     ویکی‌آمباردا
    -0.36
    Karakteristik
    -0.36
    Revenir
    -0.35
     сборной
    -0.35
     SPECIFIC
    -0.35
     ComVisible
    -0.34
    POSITIVE LOGITS
    endphp
    0.48
    Pyx
    0.48
    styleType
    0.48
    ktop
    0.47
    antwo
    0.44
    printStats
    0.43
     >=",
    0.43
     ✭✭
    0.43
    Honest
    0.43
     <=",
    0.43
    Activations Density 0.655%

    No Known Activations