© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15828
    Prev
    Next
    INDEX
    Explanations

    key descriptors related to roles, functions, and personality traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cen
    -0.50
     GenerationType
    -0.50
    withId
    -0.49
    SequentialGroup
    -0.48
    ?
    -0.48
     divisions
    -0.47
    TL
    -0.46
    heim
    -0.45
     incidente
    -0.44
     eventualmente
    -0.44
    POSITIVE LOGITS
    styleType
    0.94
    bibfield
    0.82
     faſt
    0.76
    IsContent
    0.74
    CppMethod
    0.71
    -------------</
    0.71
    MigrationBuilder
    0.69
     investissements
    0.68
     pleaſure
    0.68
     Савезне
    0.68
    Activations Density 0.446%

    No Known Activations