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. 6-GEMMASCOPE-RES-16K
    6. 2526
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significance or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     encarga
    -0.66
    Ouch
    -0.64
     поводу
    -0.61
    hidupan
    -0.58
    arraycopy
    -0.58
    HandleFunc
    -0.57
    ,"
    -0.56
    ยว
    -0.56
     nicely
    -0.54
    urdy
    -0.53
    POSITIVE LOGITS
     greater
    1.61
    Greater
    1.58
     Greater
    1.55
    greater
    1.54
    GREATER
    1.44
    maior
    1.05
     greatest
    1.02
    greatest
    1.00
     maior
    0.98
     Lesser
    0.98
    Activations Density 0.095%

    No Known Activations