© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 2524
    Prev
    Next
    INDEX
    Explanations

    phrases indicating improvement or positive changes in situations

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

    After adjectives/comparatives

    np_acts-logits-general · gemini-2.0-flash

    improvement, fixation, or positive state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     []:
    -0.62
    فاظ
    -0.54
    Décès
    -0.53
     fail
    -0.52
    Fail
    -0.52
     failed
    -0.52
    Fails
    -0.52
    esModule
    -0.51
    fail
    -0.51
     fails
    -0.50
    POSITIVE LOGITS
     improved
    1.09
     Endlich
    0.96
     finally
    0.95
    improved
    0.94
     improvements
    0.94
    finally
    0.94
    Improved
    0.92
     Improved
    0.92
     improvement
    0.92
     improves
    0.91
    Activations Density 0.382%

    No Known Activations