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. 6-GEMMASCOPE-RES-16K
    6. 191
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal responsibilities and compliance

    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
     specialising
    -0.51
    Ahoj
    -0.49
     specialises
    -0.49
    ain
    -0.48
    '][]
    -0.48
     vo
    -0.47
    ogo
    -0.46
     na
    -0.45
    ína
    -0.45
     ou
    -0.45
    POSITIVE LOGITS
     مشين
    0.88
     korrekt
    0.85
     properly
    0.84
     corretto
    0.84
     Roskov
    0.82
     autorytatywna
    0.81
    Hentet
    0.75
    properly
    0.75
    دانشنامهٔ
    0.74
     Properly
    0.74
    Activations Density 0.347%

    No Known Activations