© 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. 16-GEMMASCOPE-RES-16K
    11. 16359
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases or words

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

    Text followed by a hyphen

    np_acts-logits-general · gemini-2.0-flash

    technical error codes or notes

    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
    دانشنامهٔ
    -0.74
    TagMode
    -0.69
    PutMapping
    -0.64
    ’
    -0.63
    ンドウ
    -0.62
    Hic
    -0.60
    Rij
    -0.60
    ائج
    -0.59
    жки
    -0.58
    itect
    -0.58
    POSITIVE LOGITS
    ----------------
    1.28
    awtextra
    1.27
     -
    1.16
    Capítulo
    1.13
    ---------------
    1.11
    ">-
    1.07
    {-
    1.00
    &-
    1.00
     disambiguazione
    0.97
     -"
    0.96
    Activations Density 0.346%

    No Known Activations