© 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. 16-GEMMASCOPE-RES-16K
    11. 1303
    Prev
    Next
    INDEX
    Explanations

    phrases indicating change or transformation

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

    ending in "-ing" describing a process

    np_acts-logits-general · gemini-2.0-flash

    increasingly becoming

    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
     olmaz
    -0.48
    aurais
    -0.47
    ずっと
    -0.44
     MonoBehaviour
    -0.41
     незавершена
    -0.41
     HttpNotFound
    -0.41
     pageContext
    -0.41
    1
    -0.41
    dinga
    -0.40
    aurait
    -0.40
    POSITIVE LOGITS
     increasingly
    1.03
    increasing
    0.93
     emerging
    0.90
    slowly
    0.90
     Increasing
    0.86
    Increasing
    0.85
    EndProject
    0.84
     Slowly
    0.83
     slowly
    0.83
     increasing
    0.81
    Activations Density 0.243%

    No Known Activations