© 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-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 4518
    Prev
    Next
    INDEX
    Explanations

    mathematical or formal structures, particularly related to equations and alignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onOptions
    -0.59
    FormState
    -0.54
    HomeAsUpEnabled
    -0.53
    ValueGeneration
    -0.51
    TemporalType
    -0.49
    #+#
    -0.49
    detectChanges
    -0.47
     aDecoder
    -0.46
     ब्रेकडाउन
    -0.45
    awaiter
    -0.45
    POSITIVE LOGITS
    aligned
    1.52
    Aligned
    0.90
    eqnarray
    0.80
    align
    0.78
     aligned
    0.75
     Align
    0.70
     aligning
    0.66
    alignment
    0.63
    Align
    0.62
     Alignment
    0.60
    Activations Density 0.192%

    No Known Activations