© 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. 18-GEMMASCOPE-RES-16K
    11. 13431
    Prev
    Next
    INDEX
    Explanations

    references to experimental design and reproducibility in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Replicated or repeated experiments

    np_acts-logits-general · gemini-2.0-flash

    biological experiments repeated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.72
    BASEPATH
    -0.66
    MENAFN
    -0.60
    مصادر
    -0.59
    WithIOException
    -0.59
     nakalista
    -0.58
    writeFieldEnd
    -0.58
    }))
    -0.56
    pyplot
    -0.56
     pageContext
    -0.56
    POSITIVE LOGITS
     repeat
    2.12
     repeats
    1.93
     repeating
    1.91
     Repeat
    1.91
     repeated
    1.89
     repetition
    1.84
    repeat
    1.80
    Repeat
    1.77
     duplicate
    1.73
     replicate
    1.71
    Activations Density 0.537%

    No Known Activations