© 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. 24-GEMMASCOPE-RES-16K
    11. 15923
    Prev
    Next
    INDEX
    Explanations

    themes related to conflict and struggle

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

    Contractions with "I," "you," or "we."

    np_acts-logits-general · gemini-2.0-flash

    colloquial verb contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.59
    دانشنامهٔ
    -0.58
    ]--;
    -0.56
    Билгалдахарш
    -0.55
    herren
    -0.52
    OGND
    -0.51
    ++
    -0.51
    Искәрмәләр
    -0.50
    Configurer
    -0.49
     xrange
    -0.49
    POSITIVE LOGITS
     ain
    1.14
     aint
    0.86
     been
    0.84
     gotta
    0.81
     done
    0.80
     gon
    0.80
     gonna
    0.77
     wanna
    0.76
     Ain
    0.75
     goin
    0.70
    Activations Density 0.127%

    No Known Activations