© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 7378
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "top" or related variations that indicate ranking or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.80
     gustó
    -0.71
    iség
    -0.70
    Général
    -0.67
    }')
    -0.67
    rawdę
    -0.66
    ']=='
    -0.64
    CHD
    -0.64
    ]:
    -0.63
    ChildIndex
    -0.62
    POSITIVE LOGITS
     TOP
    1.99
     top
    1.76
    TOP
    1.75
     Top
    1.73
    Top
    1.67
     tops
    1.66
    top
    1.65
     Tops
    1.57
    getTop
    1.45
    tops
    1.31
    Activations Density 0.050%

    No Known Activations