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. 3200
    Prev
    Next
    INDEX
    Explanations

    references to actions and concepts related to challenges, goals, and UI elements

    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
     w
    -0.47
    siella
    -0.46
    Ome
    -0.44
     An
    -0.43
     Burg
    -0.43
    weka
    -0.42
     pró
    -0.42
    createTextNode
    -0.41
    bode
    -0.40
    ʐ
    -0.40
    POSITIVE LOGITS
     Roskov
    0.92
    存于互联网档案馆
    0.92
     nahilalakip
    0.91
    ⓧ
    0.90
     BorderSide
    0.82
    EndGlobalSection
    0.80
    GEBURTSDATUM
    0.79
    Erreferentziak
    0.79
    CppCodeGen
    0.77
     utafiti
    0.77
    Activations Density 1.025%

    No Known Activations