© 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. 2-GEMMASCOPE-RES-16K
    11. 12755
    Prev
    Next
    INDEX
    Explanations

    terms related to feature selection methodologies in data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DEFENDANT
    -0.41
     DONOR
    -0.38
     TELEPHONE
    -0.37
     PLAINTIFF
    -0.37
     DIAGRAM
    -0.36
    oquia
    -0.35
    InstrumentedTest
    -0.34
     APPELLANT
    -0.33
     zanahoria
    -0.33
    jooq
    -0.33
    POSITIVE LOGITS
     FS
    1.70
     GS
    1.63
    FS
    1.63
    GS
    1.61
     LS
    1.59
     TS
    1.57
    LS
    1.56
    BS
    1.55
    DS
    1.55
     DS
    1.52
    Activations Density 0.430%

    No Known Activations