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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6421
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to have."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "has" followed by a past participle

    np_acts-logits-general · gemini-2.0-flash

    has been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.56
    PerformLayout
    -0.56
     purpoſe
    -0.54
    bufio
    -0.53
     ſtate
    -0.51
    ToDecimal
    -0.50
    forKey
    -0.48
     houſe
    -0.47
     pleaſure
    -0.47
     preſent
    -0.46
    POSITIVE LOGITS
     has
    1.33
    has
    1.15
     Has
    1.09
    Has
    1.05
     have
    1.01
     been
    0.96
     HAS
    0.94
     telah
    0.92
     had
    0.92
     έχει
    0.92
    Activations Density 0.278%

    No Known Activations