© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1163
    Prev
    Next
    INDEX
    Explanations

    phrases related to confirmation and verification

    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
    مقد
    -0.57
    koning
    -0.56
    kloped
    -0.56
    cepan
    -0.52
    BeginContext
    -0.52
    ukunft
    -0.51
    phyllum
    -0.51
     beginnetje
    -0.51
    mistry
    -0.51
    cett
    -0.50
    POSITIVE LOGITS
     confirming
    1.33
     confirms
    1.31
     confirm
    1.28
     confirmation
    1.26
     confirmed
    1.22
     reinforce
    1.17
     confirmations
    1.16
     Confirmation
    1.15
     reaffirm
    1.14
     Confirmed
    1.13
    Activations Density 0.585%

    No Known Activations