© 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. 9-GEMMASCOPE-RES-16K
    11. 2300
    Prev
    Next
    INDEX
    Explanations

    references to religious texts, quotes, or notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     “
    -0.49
    </
    -0.41
    andExpect
    -0.40
     it
    -0.40
     following
    -0.39
     and
    -0.38
     atque
    -0.38
    ”
    -0.38
     publiés
    -0.38
     body
    -0.38
    POSITIVE LOGITS
    LookAnd
    1.08
     snippetHide
    1.07
     StringTokenizer
    1.04
    TypedDataSet
    1.03
    principalColumn
    0.98
    featureID
    0.96
    enderror
    0.94
    省市镇
    0.93
    ItemBackground
    0.93
     Wikimedijinoj
    0.87
    Activations Density 1.048%

    No Known Activations