© 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. 5-GEMMASCOPE-RES-16K
    11. 9552
    Prev
    Next
    INDEX
    Explanations

    nested structures or code segments, particularly in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pyplot
    -0.59
     acetic
    -0.56
     فريبيس
    -0.56
    ecute
    -0.55
     PyObject
    -0.55
     __('
    -0.52
    놨
    -0.52
     alkal
    -0.52
     שוליים
    -0.52
     Rossa
    -0.51
    POSITIVE LOGITS
    endphp
    0.93
    SourceChecksum
    0.87
    findpost
    0.87
    tvguidetime
    0.81
    rungsseite
    0.77
    )))),
    0.77
    })),
    0.73
    ))),
    0.73
    PerformLayout
    0.73
     AssemblyTitle
    0.72
    Activations Density 0.021%

    No Known Activations