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. 5-GEMMASCOPE-RES-16K
    6. 3459
    Prev
    Next
    INDEX
    Explanations

    terms related to levels, scales, or ranges in various contexts, particularly in relation to income and enterprise sizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.76
    存于互联网档案馆
    -0.66
     jspb
    -0.65
     hemispheres
    -0.63
     linkovi
    -0.62
    sApp
    -0.62
     eyelashes
    -0.59
    verständlich
    -0.58
     esternos
    -0.58
     asleep
    -0.58
    POSITIVE LOGITS
     medium
    0.82
     moderate
    0.81
     menengah
    0.81
     Medium
    0.77
     mittel
    0.77
     intermediate
    0.76
     mid
    0.76
     Moderate
    0.76
    moderate
    0.74
    medium
    0.74
    Activations Density 0.356%

    No Known Activations