© 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. 11-GEMMASCOPE-RES-16K
    11. 5043
    Prev
    Next
    INDEX
    Explanations

    phrases that involve labeling people or concepts as 'fake', 'dangerous', or derogatory, often utilizing quotes to emphasize these characterizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.66
    دانشنامهٔ
    -0.62
     ſtand
    -0.58
     autorytatywna
    -0.58
     raiſ
    -0.56
     nahilalakip
    -0.52
     houſe
    -0.51
    ⓧ
    -0.50
    曖昧さ回避
    -0.50
    httphttps
    -0.50
    POSITIVE LOGITS
    dcterms
    0.44
    fluoro
    0.44
    RestTemplate
    0.41
    賀状
    0.36
    ">:
    0.36
     gefü
    0.35
    Коммента
    0.35
     epit
    0.35
    unoz
    0.34
     Kün
    0.34
    Activations Density 0.605%

    No Known Activations