© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 1311
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to customization and tailoring of services or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.59
    setViewportView
    -0.45
    ânico
    -0.44
    NOPQRST
    -0.44
     thiện
    -0.44
     aDecoder
    -0.44
    AMM
    -0.43
     đĩa
    -0.43
     Crews
    -0.41
     Medals
    -0.41
    POSITIVE LOGITS
     tailored
    1.74
     tailor
    1.54
     customized
    1.43
     customised
    1.39
     tailoring
    1.33
     suited
    1.31
     adapted
    1.29
     personalized
    1.28
     Tailor
    1.27
     adapts
    1.25
    Activations Density 0.283%

    No Known Activations