© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 12752
    Prev
    Next
    INDEX
    Explanations

    elements pertaining to uniqueness and distinctiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eradish
    -0.43
     Inactive
    -0.42
    🦳
    -0.42
    ulongan
    -0.42
    ABASE
    -0.42
     bezeichneter
    -0.42
     wireType
    -0.41
    іе
    -0.41
     laiton
    -0.41
    izoen
    -0.41
    POSITIVE LOGITS
     unique
    3.75
    unique
    3.28
     Unique
    3.13
    Unique
    3.06
     UNIQUE
    2.89
     uniqueness
    2.88
     uniques
    2.75
     unieke
    2.70
     uniquely
    2.69
     уника
    2.63
    Activations Density 0.967%

    No Known Activations