© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 16245
    Prev
    Next
    INDEX
    Explanations

    references to vehicle engines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
    principalColumn
    -0.86
    NameInMap
    -0.82
    +#+#
    -0.82
    //
    -0.81
     kasarigan
    -0.81
     AssemblyCulture
    -0.79
    parsedMessage
    -0.78
    UrlResolution
    -0.78
    Према
    -0.78
    цездатний
    -0.77
    POSITIVE LOGITS
     engine
    1.99
     Engine
    1.86
     engines
    1.79
    Engine
    1.67
     ENGINE
    1.66
     Engines
    1.65
    engine
    1.63
    engines
    1.41
    ENGINE
    1.37
    Engines
    1.37
    Activations Density 0.027%

    No Known Activations