© 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. 12-GEMMASCOPE-RES-16K
    11. 14089
    Prev
    Next
    INDEX
    Explanations

    references to intermediate entities, stages, or layers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.71
     myſelf
    -0.63
     itſelf
    -0.61
     ISNI
    -0.59
    ativität
    -0.59
    MessageTagHelper
    -0.57
     isos
    -0.57
     perpetuity
    -0.57
    idać
    -0.57
    glBindTexture
    -0.57
    POSITIVE LOGITS
     intermediate
    0.92
    intermediate
    0.83
     intermediary
    0.80
    OGND
    0.72
    中间
    0.70
     intermédiaire
    0.69
     intermedi
    0.68
     Zwischen
    0.66
     before
    0.66
     intermedio
    0.63
    Activations Density 0.796%

    No Known Activations