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. 15802
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or interrogative expressions

    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
    MemoryWarning
    -0.64
    ntos
    -0.55
     Nouveau
    -0.54
     Spitz
    -0.53
     وظ
    -0.51
    zessin
    -0.51
     combineReducers
    -0.51
    มาย
    -0.50
    っしゃ
    -0.50
     مؤرشف
    -0.50
    POSITIVE LOGITS
     if
    1.70
    if
    1.52
     If
    1.49
    If
    1.40
     если
    1.35
     IF
    1.34
     nếu
    1.32
     Если
    1.30
     jika
    1.27
     Jeśli
    1.26
    Activations Density 0.403%

    No Known Activations