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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 7517
    Prev
    Next
    INDEX
    Explanations

    terms related to enhancement and improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.64
     IMDG
    -0.56
    StructEnd
    -0.54
    béco
    -0.51
    TRIBUN
    -0.46
    jooq
    -0.46
     abz
    -0.45
     MatDialog
    -0.45
    ioutil
    -0.44
     interloc
    -0.44
    POSITIVE LOGITS
     enhancement
    1.45
    enhance
    1.45
     Enhance
    1.43
     Enhancement
    1.41
     enhanced
    1.39
     enhance
    1.38
     Enhanced
    1.37
    Enhance
    1.31
     enhancing
    1.29
     Enhancing
    1.28
    Activations Density 0.231%

    No Known Activations