© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 7031
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and functions in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sin
    -0.68
     cherry
    -0.67
    tology
    -0.63
    ia
    -0.61
     ICP
    -0.60
    nicki
    -0.59
    vection
    -0.58
    itory
    -0.57
    ICP
    -0.56
    այի
    -0.56
    POSITIVE LOGITS
     cos
    1.04
     cosine
    1.04
    cos
    1.00
     Cos
    0.95
    AnchorStyles
    0.93
    Cos
    0.92
     BrowserModule
    0.86
    ]^{-
    0.84
    cosine
    0.83
     виправивши
    0.79
    Activations Density 0.045%

    No Known Activations