© 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. 22-GEMMASCOPE-RES-16K
    11. 5616
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and patience in the context of processing emotions

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

    Pronouns that begin sentences

    np_acts-logits-general · gemini-2.0-flash

    seeing change unfold

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sahiptir
    -0.59
     voici
    -0.50
    sounds
    -0.49
     faptul
    -0.49
    意思是
    -0.48
     göre
    -0.48
     varför
    -0.46
     partielle
    -0.46
    abab
    -0.45
     oublier
    -0.45
    POSITIVE LOGITS
     emerge
    1.18
     unfold
    1.14
     come
    1.09
     evolve
    1.05
     arrive
    1.02
     grow
    0.94
     coming
    0.93
     disappear
    0.93
     happen
    0.92
     arise
    0.87
    Activations Density 0.266%

    No Known Activations