© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 7257
    Prev
    Next
    INDEX
    Explanations

    method calls and object manipulation in programming code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ף
    -0.49
    none
    -0.48
    ONO
    -0.47
     None
    -0.46
    BagLayout
    -0.46
    //});
    -0.45
    toje
    -0.45
    ParallelGroup
    -0.44
    ones
    -0.43
    aab
    -0.43
    POSITIVE LOGITS
    NameInMap
    1.06
     AssemblyProduct
    0.97
    featureID
    0.97
    Personendaten
    0.84
    withIdentifier
    0.84
    mybatisplus
    0.80
    SerializedName
    0.80
     objectForKey
    0.78
     AssemblyTitle
    0.76
    addCriterion
    0.76
    Activations Density 0.176%

    No Known Activations