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 - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16334
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "have" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnsafeEnabled
    -0.42
    rungsseite
    -0.40
    IGraphics
    -0.36
     Wikimedijinoj
    -0.36
     Taktlose
    -0.34
     "..\..\..\
    -0.34
     "..\..\
    -0.33
    MessageTagHelper
    -0.33
     estekak
    -0.31
     betweenstory
    -0.31
    POSITIVE LOGITS
     fun
    0.77
     difficulty
    0.76
     trouble
    0.71
     recourse
    0.69
     recours
    0.63
     conversations
    0.63
    difficulty
    0.62
     access
    0.61
     gotten
    0.61
     been
    0.59
    Activations Density 0.404%

    No Known Activations