© 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. 13095
    Prev
    Next
    INDEX
    Explanations

    data representation related to scientific analysis

    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
    varlak
    -0.47
    tagen
    -0.43
    insic
    -0.41
     gré
    -0.40
     gezicht
    -0.39
     Paran
    -0.39
    lambda
    -0.37
     daun
    -0.37
     schild
    -0.37
    Paran
    -0.36
    POSITIVE LOGITS
    IsContent
    0.82
     unknownFields
    0.79
    AndroidJUnit
    0.78
    EndInit
    0.77
     beginnetje
    0.77
     saites
    0.76
    GEBURTSDATUM
    0.76
    IUrlHelper
    0.72
    __.__
    0.70
    InitVars
    0.67
    Activations Density 0.602%

    No Known Activations