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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 10080
    Prev
    Next
    INDEX
    Explanations

    references to people and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DllImport
    -0.74
     onPostExecute
    -0.69
     mourut
    -0.67
     knelt
    -0.65
    
    -0.64
    IndentedString
    -0.61
     pleaſure
    -0.59
    ждены
    -0.58
     sağlar
    -0.58
     aveug
    -0.58
    POSITIVE LOGITS
     people
    1.41
     folks
    1.30
     ppl
    1.08
     everybody
    1.06
     everyone
    1.00
     anybody
    0.97
     things
    0.95
    people
    0.95
     anyone
    0.94
     someone
    0.93
    Activations Density 0.118%

    No Known Activations