© 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. 12675
    Prev
    Next
    INDEX
    Explanations

    negative sentiment or expressions of inability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    political and societal commentary, especially discussions about economics, race, and education policy.

    oai_token-act-pair · gpt-5-nanoTriggered by @jrosseruk
    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
     objectMapper
    -0.70
     Mather
    -0.64
     Hiller
    -0.60
     genomen
    -0.60
    Kesimpulan
    -0.60
    avond
    -0.60
     Heine
    -0.59
     gerichtet
    -0.58
    هما
    -0.58
     verwijderen
    -0.58
    POSITIVE LOGITS
    t
    1.41
     not
    0.96
     Not
    0.90
    not
    0.89
    Not
    0.88
     wasnt
    0.85
     CANT
    0.83
     wont
    0.81
     isnt
    0.81
     wouldnt
    0.79
    Activations Density 0.079%

    No Known Activations