© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4812
    Prev
    Next
    INDEX
    Explanations

    specific names or terms related to music and cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.82
     виправивши
    -0.65
    MENAFN
    -0.64
    >",
    -0.64
    afficheront
    -0.63
     esternos
    -0.63
    AndEndTag
    -0.62
    aarrggbb
    -0.62
    SequentialGroup
    -0.61
    انجليز
    -0.60
    POSITIVE LOGITS
    é
    1.39
    É
    0.93
    è
    0.84
    eacute
    0.81
    és
    0.73
    ée
    0.72
     É
    0.66
    ý
    0.66
    ém
    0.65
    ré
    0.64
    Activations Density 2.429%

    No Known Activations