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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3455
    Prev
    Next
    INDEX
    Explanations

    references to government decisions and strategic actions

    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
     selve
    -0.51
     zag
    -0.49
    NameValuePair
    -0.48
    __(/*!
    -0.48
     esternos
    -0.47
     "..\..\..\
    -0.46
    ExtendWith
    -0.46
    oss
    -0.44
     fans
    -0.43
     Bar
    -0.42
    POSITIVE LOGITS
     Normdatei
    0.80
     الحره
    0.76
    الإنجليزية
    0.70
     propOrder
    0.69
     CreateTagHelper
    0.68
     كومونز
    0.67
     invokingState
    0.66
    Хьажоргаш
    0.64
     Hieronymus
    0.63
     statesman
    0.62
    Activations Density 1.043%

    No Known Activations