© 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. 9-GEMMASCOPE-RES-16K
    11. 12684
    Prev
    Next
    INDEX
    Explanations

    terms related to reversal or inversion processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The neuron detects words related to reversal or inversion, particularly "reversed" and "inverted" in technical and spatial contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ellemző
    -0.40
    amanan
    -0.39
    TextHelper
    -0.39
     señ
    -0.38
    FieldDescriptor
    -0.38
    ณา
    -0.38
    ɚ
    -0.37
    梧
    -0.36
     Waray
    -0.36
    ksiä
    -0.36
    POSITIVE LOGITS
     reverse
    2.00
     reversed
    1.88
     Reverse
    1.78
    reverse
    1.67
    Reverse
    1.66
     inverted
    1.56
     reversing
    1.55
     reverses
    1.55
    reversed
    1.54
     reversal
    1.52
    Activations Density 0.400%

    No Known Activations