© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 1494
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental science and conservation issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Flags
    -0.51
     spot
    -0.48
    ]^{-
    -0.47
     Westminster
    -0.42
     Spot
    -0.41
     flags
    -0.41
     casa
    -0.40
    spot
    -0.40
    Spot
    -0.40
     κου
    -0.40
    POSITIVE LOGITS
     prehistoric
    1.11
     ancient
    1.09
     millennia
    1.06
     centuries
    1.04
     antiquity
    1.01
    Ancient
    0.97
    ancient
    0.96
     Ancient
    0.94
     Centuries
    0.89
     historical
    0.86
    Activations Density 0.397%

    No Known Activations