Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5596
    Prev
    Next
    INDEX
    Explanations

    connections between deceptive practices and their underlying intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 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
    PerformLayout
    -0.54
     Yol
    -0.48
     foss
    -0.48
     Sied
    -0.48
     quo
    -0.47
    พาะ
    -0.47
    GetEnumerator
    -0.46
    ctico
    -0.46
    }],
    
    -0.46
    Forma
    -0.45
    POSITIVE LOGITS
     дописавши
    0.73
     createSlice
    0.69
     secretly
    0.68
    本当は
    0.68
     fake
    0.67
     faking
    0.67
     مرئيه
    0.63
     réellement
    0.59
    Geplaatst
    0.59
     beginnetje
    0.59
    Activations Density 0.318%

    No Known Activations