© 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. 20-GEMMASCOPE-RES-16K
    11. 3631
    Prev
    Next
    INDEX
    Explanations

    technical terms related to PHP coding and potential warnings or errors in code execution

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

    Code, paths, and programming syntax

    np_acts-logits-general · gemini-2.0-flash

    strict warning or code declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ->
    -1.43
    ()->
    -1.38
    ")->
    -1.16
    ']->
    -1.13
    _->
    -1.08
    )->
    -1.06
    ]->
    -1.05
    ')->
    -0.91
    ))->
    -0.89
    ::
    -0.86
    POSITIVE LOGITS
    qrstuvwxyz
    0.56
    opardy
    0.52
    StoryboardSegue
    0.52
    RTCF
    0.51
    éről
    0.50
    ïn
    0.49
    IRQn
    0.49
    zeiro
    0.48
    finals
    0.46
    rawy
    0.46
    Activations Density 0.195%

    No Known Activations