© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5251
    Prev
    Next
    INDEX
    Explanations

    references to regional or geographical contexts

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

    "regional" or "region"

    np_acts-logits-general · gemini-2.0-flash

    regional news

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.54
    Autowired
    -0.48
    SneakyThrows
    -0.43
    AndFlush
    -0.42
    Télé
    -0.41
     letzter
    -0.41
     onPostExecute
    -0.41
    󠁮
    -0.40
    multer
    -0.40
     Chartres
    -0.40
    POSITIVE LOGITS
     Region
    1.07
     region
    1.05
    region
    1.03
    endregion
    1.02
    Region
    1.00
     REGION
    0.94
     regionally
    0.88
     regions
    0.84
     Regions
    0.84
     regional
    0.83
    Activations Density 0.180%

    No Known Activations