© 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. 14-GEMMASCOPE-RES-16K
    6. 13614
    Prev
    Next
    INDEX
    Explanations

    specific coding and programming structures or components, particularly those relating to error handling, object management, and resource allocation in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.76
    __*/
    -0.69
    MigrationBuilder
    -0.66
    IntoConstraints
    -0.65
    __':
    
    -0.60
    XmlType
    -0.59
    +#+
    -0.57
    存于互联网档案馆
    -0.57
    Personendaten
    -0.57
     forState
    -0.56
    POSITIVE LOGITS
    पया
    0.66
    FieldBuilder
    0.57
    日閲覧
    0.55
    closePath
    0.53
     enfans
    0.53
    principalTable
    0.52
     natura
    0.51
     sacré
    0.51
     numerus
    0.51
     dė
    0.49
    Activations Density 0.106%

    No Known Activations