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. 16-GEMMASCOPE-RES-16K
    6. 283
    Prev
    Next
    INDEX
    Explanations

    terms related to patching, including various forms of the word "patch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    containing "atch" (patch, batch, catch)

    np_acts-logits-general · gemini-2.0-flash

    patch, batch, dash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ränkt
    -0.86
    complexContent
    -0.80
    ọi
    -0.78
     aVar
    -0.78
     Teo
    -0.76
    tena
    -0.76
    oas
    -0.75
    styleType
    -0.75
     disambiguazione
    -0.74
     Infórmanos
    -0.74
    POSITIVE LOGITS
    s
    1.06
     Hach
    0.98
    hhhhhhhh
    0.88
    hhhh
    0.88
    iness
    0.82
    ich
    0.82
     Tash
    0.81
    hhh
    0.81
    ASH
    0.80
     Wich
    0.79
    Activations Density 0.385%

    No Known Activations