© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13849
    Prev
    Next
    INDEX
    Explanations

    punctuation and separator characters in the text

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

    Code with find/replace functionality

    np_acts-logits-general · gemini-2.0-flash

    function arguments `dir`, `mcase`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Chars
    -0.48
     nodeId
    -0.47
    fenster
    -0.45
    .
    -0.45
    '
    -0.44
    -
    -0.44
    -(
    -0.43
    “
    -0.43
    婿
    -0.43
    ür
    -0.42
    POSITIVE LOGITS
    Personendaten
    1.37
    MigrationBuilder
    1.20
     Paglinawan
    1.10
    verwijspagina
    1.09
    Autoritní
    1.07
    ImageContext
    1.06
    }(),
    1.06
    webElementXpaths
    1.05
    +#+#
    1.02
    UnsafeEnabled
    1.01
    Activations Density 0.211%

    No Known Activations