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. 13-GEMMASCOPE-RES-16K
    6. 15818
    Prev
    Next
    INDEX
    Explanations

    references to controversial political issues or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -1.01
    RuleContext
    -0.93
     createSlice
    -0.80
     useParams
    -0.80
    ]")]
    -0.78
    sizeCache
    -0.76
     الرياضيه
    -0.75
     дописавши
    -0.74
    endphp
    -0.73
     Atm
    -0.71
    POSITIVE LOGITS
    <em>
    0.74
     folks
    0.73
     blog
    0.69
    <i>
    0.67
     http
    0.67
      
    0.67
    Â
    0.65
    http
    0.59
     my
    0.59
     I
    0.58
    Activations Density 1.090%

    No Known Activations