© 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. 12-GEMMASCOPE-RES-16K
    11. 3916
    Prev
    Next
    INDEX
    Explanations

    technical mathematical concepts related to equations and iterative methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zewod
    -0.37
    une
    -0.36
     olup
    -0.36
     mount
    -0.36
    Mount
    -0.35
     nhất
    -0.35
    kkue
    -0.34
     alpin
    -0.34
     Mount
    -0.33
     commencement
    -0.32
    POSITIVE LOGITS
    DebuggerNonUser
    0.88
    EndContext
    0.84
    ReusableCell
    0.82
    }}^{(
    0.79
    出版年
    0.77
    ImageContext
    0.76
    WriteTagHelper
    0.75
    errHandler
    0.74
     InputDecoration
    0.74
    TargetException
    0.74
    Activations Density 0.445%

    No Known Activations