© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 15865
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "init" related to function initialization in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McCar
    -0.79
    ToMany
    -0.77
     springfox
    -0.72
    bukkit
    -0.71
    ומות
    -0.64
    ETRIC
    -0.58
    kadot
    -0.58
    (/\
    -0.57
    qvarna
    -0.57
     Stro
    -0.56
    POSITIVE LOGITS
    INIT
    1.45
     INIT
    1.43
    init
    1.43
     init
    1.35
     Init
    1.34
    Init
    1.32
     Initializes
    1.15
     initState
    1.11
     initialization
    1.06
     初始化
    1.05
    Activations Density 0.048%

    No Known Activations