© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 8392
    Prev
    Next
    INDEX
    Explanations

    references to salt and its related concepts or effects

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

    "salt"

    np_acts-logits-general · gemini-2.0-flash

    salt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McCulloch
    -0.84
    enterOuterAlt
    -0.82
     Beale
    -0.78
     Pyle
    -0.76
     Hendrix
    -0.72
    ymce
    -0.72
    Hend
    -0.70
     Bevan
    -0.69
    Rory
    -0.68
    клопе
    -0.68
    POSITIVE LOGITS
     Salz
    1.46
     SALT
    1.33
     Sal
    1.32
     Salt
    1.31
    Sal
    1.30
    SALT
    1.24
     SAL
    1.24
    Salt
    1.20
     sal
    1.18
     Salter
    1.18
    Activations Density 0.424%

    No Known Activations