© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 13138
    Prev
    Next
    INDEX
    Explanations

    sentences or statements indicating questions or thoughts about the natural world

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ***!
    -0.51
     Comunicación
    -0.50
    sipasi
    -0.48
    Thunk
    -0.47
    ండి
    -0.46
    brainly
    -0.45
     telefónica
    -0.44
    tka
    -0.43
    hashi
    -0.43
    cetti
    -0.43
    POSITIVE LOGITS
    adaptiveStyles
    0.90
     nature
    0.84
    Natur
    0.79
     natural
    0.78
     natur
    0.77
     natu
    0.76
    protoimpl
    0.76
     natura
    0.75
    natur
    0.75
    Nature
    0.74
    Activations Density 0.235%

    No Known Activations