© 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. 13243
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and questions concerning moral or ethical implications

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

    Word after "if"

    np_acts-logits-general · gemini-2.0-flash

    conditional clauses and sentences

    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
     ModelExpression
    -0.53
    '])->
    -0.51
     usually
    -0.49
    Spire
    -0.47
     surprisingly
    -0.45
    beza
    -0.44
     Usually
    -0.44
    Usually
    -0.44
    usually
    -0.43
    ]),
    -0.42
    POSITIVE LOGITS
     prétend
    0.69
     esternos
    0.69
     indeed
    0.65
     fakty
    0.65
     inderdaad
    0.65
     memang
    0.64
     benar
    0.64
    truly
    0.63
    contentLoaded
    0.62
    windowFixed
    0.61
    Activations Density 0.199%

    No Known Activations