© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 314
    Prev
    Next
    INDEX
    Explanations

    references to elevated locations and viewpoints

    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
    UnsafeEnabled
    -0.58
     AssemblyTitle
    -0.57
    CodedInputStream
    -0.53
    )++;
    -0.51
    ParallelGroup
    -0.51
    NSYLVANIA
    -0.51
    ixas
    -0.47
    ldb
    -0.46
    gbaar
    -0.46
    nipeg
    -0.45
    POSITIVE LOGITS
     vantage
    0.86
     balcony
    0.75
     perched
    0.73
     overlooking
    0.69
     observation
    0.69
     Viewing
    0.67
     Observation
    0.66
     atop
    0.65
     viewing
    0.65
     Balcony
    0.65
    Activations Density 0.172%

    No Known Activations