© 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. 15-GEMMASCOPE-RES-16K
    11. 2061
    Prev
    Next
    INDEX
    Explanations

    phrases related to software operation and development issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.59
     unknownFields
    -0.57
     Italijani
    -0.56
    verwijspagina
    -0.54
    abestanden
    -0.54
    leştir
    -0.53
     defStyleAttr
    -0.52
     архивлан
    -0.50
     يتيمه
    -0.50
    //</
    -0.49
    POSITIVE LOGITS
     someone
    0.83
    Someone
    0.82
     Someone
    0.81
    someone
    0.76
     Somebody
    0.73
     somebody
    0.73
    somebody
    0.72
    Somebody
    0.71
     SOMEONE
    0.68
     iemand
    0.68
    Activations Density 0.442%

    No Known Activations