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. 1-GEMMASCOPE-RES-16K
    6. 10216
    Prev
    Next
    INDEX
    Explanations

    terms related to maintaining or supporting systems and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.66
    PyErr
    -0.65
    buttonBar
    -0.62
     useRouter
    -0.59
     jsPsych
    -0.53
    flüs
    -0.52
     inspiré
    -0.52
    _("
    -0.51
     Савезне
    -0.51
    خصة
    -0.51
    POSITIVE LOGITS
     maintained
    3.11
     maintain
    3.09
     maintaining
    3.01
     maintenance
    2.89
     Maintaining
    2.86
    maintain
    2.85
     Maintain
    2.82
     maintains
    2.82
    Maintaining
    2.81
    Maintain
    2.73
    Activations Density 0.081%

    No Known Activations