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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4546
    Prev
    Next
    INDEX
    Explanations

    topics related to project support and future directions

    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
    GraphicsUnit
    -0.62
    Personensuche
    -0.59
     незавершена
    -0.51
     présidenti
    -0.50
    TestingModule
    -0.49
     يتيمه
    -0.48
     mentality
    -0.47
     समीक्षाओं
    -0.47
    slidesPer
    -0.47
    Vidu
    -0.46
    POSITIVE LOGITS
    BagLayout
    0.62
    DockStyle
    0.61
     MainAxisSize
    0.61
    IPAC
    0.60
     $_"
    0.59
    kháu
    0.59
    HOY
    0.59
    Howdy
    0.58
    haviour
    0.57
    ocino
    0.57
    Activations Density 0.992%

    No Known Activations