© 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. 4-GEMMASCOPE-RES-16K
    11. 10021
    Prev
    Next
    INDEX
    Explanations

    code structures and definitions related to programming and data types

    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
     
    -0.70
    <eos>
    -0.59
    <strong>
    -0.49
    κης
    -0.43
    <b>
    -0.41
    álogo
    -0.40
     optimis
    -0.40
    引
    -0.40
    ylle
    -0.39
    フェ
    -0.39
    POSITIVE LOGITS
     Chwiliwch
    1.10
    ViewImports
    1.03
     betweenstory
    0.95
    TagHelper
    0.92
    Hentet
    0.92
     ModelExpression
    0.91
     resourceCulture
    0.90
     мәкал
    0.90
    principalTable
    0.88
    ChildScrollView
    0.88
    Activations Density 1.384%

    No Known Activations