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

    Neuronpedia

    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. 39-GEMMASCOPE-RES-16K
    11. 410
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to database management and SQL syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.51
    enumii
    -0.49
     hydroxy
    -0.49
    featureID
    -0.47
     linkovi
    -0.45
    ביוגרפיה
    -0.44
    RTLR
    -0.43
    RTLD
    -0.43
     regenerate
    -0.43
    zsche
    -0.42
    POSITIVE LOGITS
     syntax
    0.90
    syntax
    0.68
     Syntax
    0.68
    语法
    0.66
    Syntax
    0.66
     syntactic
    0.63
     shorthand
    0.56
     synt
    0.54
     notation
    0.53
     sinta
    0.53
    Activations Density 1.552%

    No Known Activations