© 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. 4396
    Prev
    Next
    INDEX
    Explanations

    Javascript function definitions and UI interaction components

    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
    setFill
    -0.46
    AspNetCore
    -0.46
    nels
    -0.46
    leto
    -0.44
    tml
    -0.43
    Ouest
    -0.43
    vos
    -0.43
    trim
    -0.42
    enumi
    -0.42
    খ
    -0.41
    POSITIVE LOGITS
     EconPapers
    1.02
     defaultstate
    0.96
    InvalidProtocol
    0.86
     toggle
    0.80
    WriteTagHelper
    0.76
     togg
    0.72
    protoimpl
    0.69
     ComVisible
    0.67
     GenerationType
    0.66
    toggle
    0.65
    Activations Density 0.130%

    No Known Activations