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. 14-GEMMASCOPE-RES-16K
    6. 4285
    Prev
    Next
    INDEX
    Explanations

    terms related to capacity in various contexts

    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
     Gunt
    -0.94
    IntoConstraints
    -0.85
     mergeFrom
    -0.79
    Kend
    -0.79
     ویکی‌پدی
    -0.78
    AccessorTable
    -0.76
     Ols
    -0.75
     reft
    -0.75
     lyre
    -0.73
     Efq
    -0.72
    POSITIVE LOGITS
    capacity
    1.16
     capacity
    1.15
     Capacity
    1.15
     capacities
    1.08
     CAPACITY
    1.07
    CAPACITY
    1.05
    Capacity
    1.03
     Capac
    0.81
    _{-\
    0.79
    vspace
    0.76
    Activations Density 0.102%

    No Known Activations