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. 6863
    Prev
    Next
    INDEX
    Explanations

    references to tubes or similar cylindrical structures

    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
    GeneratedValue
    -0.69
    StandardCharsets
    -0.67
     تضيفلها
    -0.67
    хьтан
    -0.62
    NameInMap
    -0.59
     Morty
    -0.58
     mapStateToProps
    -0.58
    abetes
    -0.57
     ujednoznacz
    -0.57
    calientes
    -0.57
    POSITIVE LOGITS
     tube
    3.80
     tubes
    3.63
     Tube
    3.43
    tube
    3.41
    Tube
    3.19
     TUBE
    3.16
     Tubes
    3.16
    tubes
    2.84
     tubo
    2.22
     tubos
    2.21
    Activations Density 0.018%

    No Known Activations