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. 4-GEMMASCOPE-RES-16K
    6. 11396
    Prev
    Next
    INDEX
    Explanations

    code snippets that assign or update variables in a programming context

    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
     &___
    -0.66
    FieldBuilder
    -0.57
     getBase
    -0.56
    etone
    -0.56
     Houſe
    -0.56
    antur
    -0.55
    cipit
    -0.55
    oczes
    -0.54
     IconButton
    -0.54
     "-";
    -0.54
    POSITIVE LOGITS
     ddelweddau
    0.55
     الدولى
    0.53
    mobileqq
    0.51
    createClass
    0.50
    mybatisplus
    0.49
    DockStyle
    0.48
     XCTest
    0.47
     MonoBehaviour
    0.47
    Eloquent
    0.47
     okuyayım
    0.45
    Activations Density 0.086%

    No Known Activations