© 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. 9494
    Prev
    Next
    INDEX
    Explanations

    keywords related to government and political structures

    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
     Monfieur
    -1.30
     myſelf
    -1.26
     purpoſe
    -1.24
     houſe
    -1.21
     Efq
    -1.16
     Reſ
    -1.15
     Houſe
    -1.15
     pleaſure
    -1.14
     Jefus
    -1.12
     Majefty
    -1.12
    POSITIVE LOGITS
     €
    0.77
     (€
    0.74
     European
    0.74
    ########.
    0.63
     Euro
    0.63
    European
    0.62
     EU
    0.61
     Europe
    0.59
     européenne
    0.58
     euros
    0.58
    Activations Density 1.359%

    No Known Activations