© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 8933
    Prev
    Next
    INDEX
    Explanations

    patterns in structured data or code syntax, particularly involving brackets and numerical representations

    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
     estekak
    -0.89
     AssemblyProduct
    -0.83
     externi
    -0.81
    /**
    -0.79
    SourceChecksum
    -0.78
     hObject
    -0.76
    verwijspagina
    -0.75
     ISNI
    -0.73
    ISupport
    -0.72
    rungsseite
    -0.69
    POSITIVE LOGITS
    SizeF
    0.48
     BoxFit
    0.46
    [][
    0.45
    {}/
    0.45
    anwal
    0.44
    folgen
    0.44
    exels
    0.43
    ilber
    0.43
    iente
    0.43
    География
    0.42
    Activations Density 0.835%

    No Known Activations