© 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. 37-GEMMASCOPE-RES-16K
    11. 5723
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "Car" followed by various suffixes and related terms, likely reflecting a focus on specific companies or contexts involving "Car."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTHOOK
    -0.47
    EditorBrowsable
    -0.44
    Datuak
    -0.44
     character
    -0.43
    exitRule
    -0.39
    ?}",
    -0.39
    chartInstance
    -0.39
    Архівовано
    -0.39
    Superview
    -0.39
    characteristics
    -0.38
    POSITIVE LOGITS
     فريبيس
    0.46
    ViewInit
    0.44
     OMITTED
    0.43
    ManagedBean
    0.42
     mettez
    0.40
    interopRequire
    0.40
     bancaire
    0.40
    ArgsConstructor
    0.40
    stdc
    0.39
    hydrates
    0.39
    Activations Density 0.183%

    No Known Activations