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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122863
    Prev
    Next
    INDEX
    Explanations

    the word forms of "continue" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $_['
    -0.54
    artments
    -0.52
     éc
    -0.48
    Sheikh
    -0.47
    ärke
    -0.44
    Kelas
    -0.44
    Sheldon
    -0.44
     lockers
    -0.44
     Gór
    -0.43
    artment
    -0.43
    POSITIVE LOGITS
     Continue
    1.09
    continue
    1.01
     Continues
    0.99
     continued
    0.98
     continue
    0.98
    Continue
    0.96
     continuance
    0.94
     Continued
    0.91
     Continuation
    0.91
     continuing
    0.91
    Activations Density 0.022%

    No Known Activations