© 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. 14709
    Prev
    Next
    INDEX
    Explanations

    phrases indicating understanding or comprehension of complex information

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

    "According to" or "as far as I can"

    np_acts-logits-general · gemini-2.0-flash

    according to or as far as

    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
     contextLoads
    -0.72
    latego
    -0.68
    principalTable
    -0.67
     Vikipedi
    -0.64
    kfree
    -0.60
    chyma
    -0.60
     Autres
    -0.57
     חיצוניים
    -0.57
     Inscrivez
    -0.56
    apimachinery
    -0.56
    POSITIVE LOGITS
     ACCORD
    0.61
    Según
    0.57
    EDEFAULT
    0.56
    according
    0.55
    Selon
    0.53
     According
    0.51
     Menurut
    0.50
    According
    0.50
     according
    0.50
     según
    0.49
    Activations Density 0.215%

    No Known Activations