Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 14982
    Prev
    Next
    INDEX
    Explanations

    terms related to equipment or features of devices and vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TemporalType
    -0.73
    🎰
    -0.70
    Indented
    -0.65
    flasche
    -0.64
    HasColumnType
    -0.62
     Ith
    -0.61
     useRouter
    -0.60
    PostExecute
    -0.58
     χώ
    -0.57
    ecare
    -0.57
    POSITIVE LOGITS
     equipped
    0.92
     equipping
    0.89
    ENABLED
    0.87
    Equipped
    0.82
     equip
    0.78
    equipped
    0.77
     Equipped
    0.73
     equi
    0.72
     coupled
    0.67
     arising
    0.66
    Activations Density 0.089%

    No Known Activations