© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28900
    Prev
    Next
    INDEX
    Explanations

    annotations related to parameter definitions in code documentation

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

    api documentation tags like @param, @return

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     héri
    -0.51
    älä
    -0.49
    ktır
    -0.48
     alpina
    -0.48
    malıdır
    -0.47
     vectorielles
    -0.47
     kuat
    -0.45
     quæ
    -0.45
    內容
    -0.44
     køb
    -0.44
    POSITIVE LOGITS
    XmlAccessorType
    0.92
     disambiguazione
    0.82
     autorytatywna
    0.79
    enumi
    0.76
    exitRule
    0.74
    CreateModel
    0.73
    Kjelder
    0.72
     BoxDecoration
    0.71
    providedIn
    0.71
    ɵɵelementStart
    0.69
    Activations Density 0.004%

    No Known Activations