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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 2237
    Prev
    Next
    INDEX
    Explanations

    phrases related to expectations and claims

    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
    ftagPool
    -0.87
    asymp
    -0.86
    ViewFeatures
    -0.84
    httphttps
    -0.72
    chartInstance
    -0.69
     ApiException
    -0.69
     Schrö
    -0.68
    apimachinery
    -0.68
     GenerationType
    -0.64
     Tr
    -0.64
    POSITIVE LOGITS
     Needed
    1.60
     needed
    1.53
    Needed
    1.44
    needed
    1.38
     NEEDED
    1.37
     required
    1.14
     Required
    1.11
     wanted
    1.03
     WANTED
    1.02
     REQUIRED
    1.01
    Activations Density 0.165%

    No Known Activations