© 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. 2-GEMMASCOPE-RES-16K
    6. 4281
    Prev
    Next
    INDEX
    Explanations

    the word "vast" and its variations, as well as forms of the word "des."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.58
    ContentAlignment
    -0.51
     Moore
    -0.50
    h
    -0.49
    der
    -0.49
    erdo
    -0.48
    ity
    -0.48
     particulières
    -0.48
    ленная
    -0.47
    UCC
    -0.47
    POSITIVE LOGITS
     ihres
    0.89
     seines
    0.89
    /**
    0.88
    WriteBarrier
    0.86
    parsedMessage
    0.86
     Roskov
    0.84
     виправивши
    0.83
    addGap
    0.82
     Ihres
    0.80
    lamabad
    0.80
    Activations Density 0.076%

    No Known Activations