© 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. 2-GEMMASCOPE-RES-16K
    11. 15335
    Prev
    Next
    INDEX
    Explanations

    instances of numbers, particularly those in the sequence of two to four

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    CloseOperation
    -0.58
    SharedDtor
    -0.51
    SourceChecksum
    -0.50
    +#+#
    -0.47
    clusal
    -0.46
     fieltro
    -0.46
     LIABLE
    -0.45
     six
    -0.44
     saveiro
    -0.44
    blurRadius
    -0.44
    POSITIVE LOGITS
     Two
    2.19
     Three
    2.02
    Two
    1.91
    Three
    1.77
     Four
    1.71
     Five
    1.62
    Four
    1.57
    Five
    1.48
     Zwei
    1.40
     Six
    1.36
    Activations Density 0.223%

    No Known Activations