© 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. 33-GEMMASCOPE-RES-16K
    11. 13203
    Prev
    Next
    INDEX
    Explanations

    mathematical structures and properties related to algebra and set theory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    typeorm
    -0.44
     Luar
    -0.44
     nakalista
    -0.43
    ="&#
    -0.42
    早
    -0.39
     للاسماء
    -0.39
    bee
    -0.36
    倒
    -0.36
    shadowRadius
    -0.36
    esModule
    -0.36
    POSITIVE LOGITS
     sequences
    0.62
    ReusableCell
    0.54
     sequence
    0.54
     nonnegative
    0.52
    sequences
    0.46
    sequence
    0.44
     nonzero
    0.44
     legal
    0.43
     secuencia
    0.43
     sufficiently
    0.42
    Activations Density 2.006%

    No Known Activations