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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-GEMMASCOPE-RES-16K
    6. 12366
    Prev
    Next
    INDEX
    Explanations

    phrases concerning cloud-related processes or modal verbs

    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
     réponses
    -0.68
    schirm
    -0.57
     density
    -0.54
     McGovern
    -0.54
     huom
    -0.53
     densité
    -0.52
     encu
    -0.52
     lượng
    -0.50
    employment
    -0.50
     tárgy
    -0.49
    POSITIVE LOGITS
     es
    1.00
     chase
    0.84
     bon
    0.83
     Bon
    0.81
     Es
    0.79
    Bon
    0.78
     kiss
    0.75
     doors
    0.72
    Es
    0.70
     chases
    0.69
    Activations Density 0.234%

    No Known Activations