© 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 EvalsExportsinterp-engineNEWAPI 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. 604
    Prev
    Next
    INDEX
    Explanations

    technical or programming language constructs related to file paths and data structures

    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
    viewDidLoad
    -0.81
     мәкал
    -0.79
    ParallelGroup
    -0.74
     Efq
    -0.72
    Personendaten
    -0.71
    makeConstraints
    -0.68
    帖最后由
    -0.67
    WireFormat
    -0.65
     NSCoder
    -0.64
    ngOnDestroy
    -0.64
    POSITIVE LOGITS
    以此
    0.44
     idéia
    0.42
    zema
    0.41
    hofen
    0.39
     فريبيس
    0.38
    meda
    0.38
     bedo
    0.38
    kende
    0.38
    ytte
    0.37
    殆
    0.37
    Activations Density 0.737%

    No Known Activations