© 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 - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1085
    Prev
    Next
    INDEX
    Explanations

    questions and statements related to memory and recollection of events

    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
     فريبيس
    -0.67
    canestro
    -0.62
    :\/\/
    -0.56
    Ārējās
    -0.55
    NewUrlParser
    -0.54
     références
    -0.50
    μφωνα
    -0.48
    etheless
    -0.48
    MigrationBuilder
    -0.48
     &&
    
    -0.48
    POSITIVE LOGITS
     precisione
    0.58
    InjectAttribute
    0.57
    enumi
    0.56
     registrazione
    0.56
    RemoveField
    0.54
    DispatchToProps
    0.54
     quelquefois
    0.53
    henswürdigkeiten
    0.51
     venuto
    0.51
    पया
    0.51
    Activations Density 0.217%

    No Known Activations