© 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. 11094
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to upward trends or improvements

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

    upward movement or progress

    np_acts-logits-general · gemini-2.0-flash

    ascend, rise, up

    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
     wh
    -0.49
    ura
    -0.49
     nonatomic
    -0.48
    llywood
    -0.47
     Gabor
    -0.47
     Tiefe
    -0.47
    textit
    -0.46
    Autowired
    -0.45
    </i>
    -0.45
    __["
    -0.43
    POSITIVE LOGITS
    ↑↑
    1.03
    👆
    0.97
    ↑↑↑
    0.95
     Above
    0.86
     ABOVE
    0.84
     BorderRadius
    0.83
    ⬆
    0.82
    Lift
    0.81
     lifts
    0.81
     👆
    0.81
    Activations Density 0.484%

    No Known Activations