© 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. 18-GEMMASCOPE-RES-16K
    11. 6651
    Prev
    Next
    INDEX
    Explanations

    technical terms and entities related to system functionality and database management

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

    Proper nouns followed by verbs indicating belief or opinion

    np_acts-logits-general · gemini-2.0-flash

    Erie, Kiki, College actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arisen
    -0.43
     køb
    -0.43
     получается
    -0.43
     constituyen
    -0.40
     pertenecen
    -0.40
     contenir
    -0.40
     flown
    -0.40
     demeure
    -0.40
     blown
    -0.40
     resultan
    -0.38
    POSITIVE LOGITS
     has
    1.18
     took
    1.05
     knew
    1.03
     thinks
    1.02
     chose
    1.01
     knows
    1.00
     wants
    0.99
     had
    0.99
     believes
    0.97
     expects
    0.96
    Activations Density 1.083%

    No Known Activations