© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6152
    Prev
    Next
    INDEX
    Explanations

    references to directory structures and file management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.90
     Anſ
    -0.88
     transférez
    -0.87
     occaf
    -0.85
    gunas
    -0.82
     tranſ
    -0.82
     raiſ
    -0.82
    uspiel
    -0.81
     ExecuteAsync
    -0.80
     Nunn
    -0.80
    POSITIVE LOGITS
     dir
    2.02
    dir
    2.01
     Dir
    2.01
    Dir
    1.93
    DIR
    1.77
     dirs
    1.67
     directory
    1.66
    dirs
    1.65
     DIR
    1.58
    Dirs
    1.56
    Activations Density 0.055%

    No Known Activations