© 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. 2-GEMMASCOPE-RES-16K
    11. 14855
    Prev
    Next
    INDEX
    Explanations

    definite articles and their variations in German text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lež
    -0.53
     piş
    -0.48
     aiment
    -0.47
     Geset
    -0.46
    amico
    -0.46
     gând
    -0.45
     memas
    -0.45
    lichem
    -0.45
     Peut
    -0.45
     voordeel
    -0.44
    POSITIVE LOGITS
     die
    1.69
    Die
    1.45
     Die
    1.40
     DIE
    1.27
    die
    1.22
     ihre
    1.22
    DIE
    1.12
     unsere
    1.07
     diese
    1.06
     Ihre
    1.04
    Activations Density 0.020%

    No Known Activations