© 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. 10-GEMMASCOPE-RES-16K
    6. 12128
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals and their roles or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.48
    etwork
    -0.47
     o
    -0.46
    vábbi
    -0.46
    lej
    -0.45
    ogh
    -0.44
    ガキ
    -0.43
    paravant
    -0.42
    jka
    -0.42
    chauer
    -0.41
    POSITIVE LOGITS
     Roskov
    0.71
     ISNI
    0.71
    parsedMessage
    0.69
    RefNanny
    0.69
     AssemblyVersion
    0.68
    AndEndTag
    0.66
     OnTriggerEnter
    0.66
     nakalista
    0.64
     Phry
    0.64
    KURZBESCHREIBUNG
    0.64
    Activations Density 0.797%

    No Known Activations