© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11108
    Prev
    Next
    INDEX
    Explanations

    affirmative and negative modal verbs indicating possibility, obligation, and intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    といけない
    -0.68
    AddHtmlAttribute
    -0.63
    utilisons
    -0.62
     surla
    -0.61
    ########.
    -0.57
     fashiola
    -0.56
     snippetHide
    -0.56
     好文分享
    -0.55
    𞤑
    -0.54
    <unused43>
    -0.54
    POSITIVE LOGITS
    !
    0.71
    ?
    0.65
    ;
    0.62
     ;)
    0.49
     because
    0.49
     :)
    0.48
     unless
    0.48
     çünkü
    0.47
    !!
    0.47
    .
    0.46
    Activations Density 0.411%

    No Known Activations