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. 23-GEMMASCOPE-RES-16K
    6. 11999
    Prev
    Next
    INDEX
    Explanations

    key attributes of products related to durability and longevity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EINVAL
    -0.56
    írus
    -0.52
     vapa
    -0.50
    kani
    -0.50
     enrolling
    -0.48
     quadrature
    -0.47
    нали
    -0.47
    astify
    -0.47
    idopsis
    -0.47
     vorbereitet
    -0.46
    POSITIVE LOGITS
     lifespan
    1.60
     longevity
    1.48
     lifetime
    1.43
    lifetime
    1.27
     lifetimes
    1.25
     durability
    1.21
     lasting
    1.15
     lasted
    1.14
    寿命
    1.12
     life
    1.12
    Activations Density 0.241%

    No Known Activations