© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 4413
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their bonding properties

    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
     strainer
    -0.83
    awtextra
    -0.77
     distanciation
    -0.71
    CreateModel
    -0.69
     Malvern
    -0.67
     liệt
    -0.66
     inqui
    -0.64
     GTS
    -0.63
     Plc
    -0.63
     Stra
    -0.63
    POSITIVE LOGITS
    hydrogen
    0.81
    Hydrogen
    0.68
    tlement
    0.68
    LookAnd
    0.67
     /\.(
    0.63
     hydrogen
    0.63
     cebolla
    0.62
     Hydrogen
    0.61
    SequentialGroup
    0.61
    ldb
    0.60
    Activations Density 0.448%

    No Known Activations