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. 8-GEMMASCOPE-RES-16K
    6. 15163
    Prev
    Next
    INDEX
    Explanations

    references to Java collections and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cyfeiriadau
    -0.63
     conquerors
    -0.63
     <<<<<<<<<<<<<<
    -0.62
    BeginContext
    -0.62
     Aristi
    -0.61
    istisches
    -0.60
    #+#
    -0.60
    ☚
    -0.56
    seende
    -0.56
    ARDI
    -0.56
    POSITIVE LOGITS
    AnchorStyles
    1.24
    <thead>
    1.16
    DoubleQuotes
    1.10
     CreateTagHelper
    0.91
     propOrder
    0.76
    WEBPACK
    0.73
    DrawerToggle
    0.69
    ########.
    0.69
    ViewFeatures
    0.69
     BorderSide
    0.67
    Activations Density 0.005%

    No Known Activations