© 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. 33-GEMMASCOPE-RES-16K
    11. 11066
    Prev
    Next
    INDEX
    Explanations

    numeric and structured data elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.87
    MemoryWarning
    -0.79
    BeginContext
    -0.76
     للاسماء
    -0.69
    NameInMap
    -0.68
    RegressionTest
    -0.67
     referenties
    -0.64
    RuleContext
    -0.64
    mtrl
    -0.63
    featureID
    -0.63
    POSITIVE LOGITS
     fifth
    1.09
     Fifth
    0.99
    Fifth
    0.91
    fifth
    0.84
     quinto
    0.82
     FIFTH
    0.82
     cinquième
    0.80
    ⑤
    0.79
     five
    0.77
    5
    0.75
    Activations Density 0.836%

    No Known Activations