Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 722
    Prev
    Next
    INDEX
    Explanations

    occurrences of the `__init__` method in class definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.74
     оригіналу
    -0.70
    CloseOperation
    -0.68
    mappedBy
    -0.67
    Šaltiniai
    -0.67
     Pfe
    -0.64
    ]++;
    -0.63
    들에게
    -0.63
    webElementXpaths
    -0.60
     multiplic
    -0.60
    POSITIVE LOGITS
    init
    2.39
     init
    2.00
    Init
    1.63
    INIT
    1.61
     Init
    1.49
     INIT
    1.41
     initState
    0.99
    onInit
    0.96
     initView
    0.84
     initData
    0.82
    Activations Density 0.098%

    No Known Activations