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. 13406
    Prev
    Next
    INDEX
    Explanations

    phrases related to difficulties and challenges in understanding or performing tasks

    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
     Leopoldo
    -0.69
     apparaître
    -0.65
     Adieu
    -0.64
     dissipation
    -0.64
     '+':
    -0.63
     Gaetano
    -0.63
     dispensed
    -0.62
     unwritten
    -0.62
     wors
    -0.61
     admixture
    -0.61
    POSITIVE LOGITS
     doing
    0.96
     getting
    0.92
     being
    0.91
    évaluateur
    0.82
    brainly
    0.81
     keeping
    0.79
     vouloir
    0.79
    TimerTask
    0.79
     having
    0.79
     making
    0.79
    Activations Density 0.532%

    No Known Activations