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. 5-GEMMASCOPE-RES-16K
    6. 2151
    Prev
    Next
    INDEX
    Explanations

    derogatory or insulting terms used to describe people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spea
    -0.47
    ])->
    -0.45
    väl
    -0.45
    wię
    -0.45
    英語版
    -0.44
    }=\{
    -0.43
    Produzione
    -0.42
    SequentialGroup
    -0.42
    BeginInit
    -0.42
    δί
    -0.42
    POSITIVE LOGITS
     bastard
    1.04
     idiot
    0.94
     bastards
    0.94
     scum
    0.93
     Bastard
    0.92
     idiots
    0.90
     morons
    0.88
     moron
    0.87
     asshole
    0.86
    umbag
    0.86
    Activations Density 0.225%

    No Known Activations