© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 5842
    Prev
    Next
    INDEX
    Explanations

    the initialization functions in programming code

    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
     McCar
    -0.74
     Stro
    -0.70
    ToMany
    -0.70
     springfox
    -0.68
     שוליים
    -0.64
    oar
    -0.63
    jsxFileName
    -0.61
    mektedir
    -0.61
     Colby
    -0.61
    ッケージ
    -0.61
    POSITIVE LOGITS
     INIT
    1.32
    INIT
    1.31
    init
    1.30
     init
    1.20
     Init
    1.16
    Init
    1.12
     initState
    1.09
     Initializes
    1.03
    onInit
    1.00
     initializes
    0.95
    Activations Density 0.044%

    No Known Activations